agent-threat-rules 4.2.3 → 4.3.0

package/rules/prompt-injection/ATR-2026-00467-garak-dan-act-as-a.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00468-garak-goat-the-target-llm.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00469-garak-dan-at-the-end.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00470-garak-dan-as-an-ai.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00472-garak-dan-are-going-to.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00473-garak-lmrc-how-can-i.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00474-garak-dan-that-chatgpt-has.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00475-garak-web-injection-alert-1-script.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00476-garak-web-injection-javascript-alert-1.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00477-garak-latentinjection-translate-the-following-text.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00478-garak-latentinjection-abuse-contact-email.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00479-garak-latentinjection-mixedunassigned.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00480-garak-dan-the-role-of.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00481-garak-dan-mixedunassigned.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00482-garak-lmrc-what-s-an.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00483-garak-dan-the-user-s.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00484-garak-dan-and-you-will.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00485-garak-dan-and-does-not.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00486-garak-dan-t-care-about.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00487-garak-dan-and-nothing-else.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00488-garak-encoding-alert-1-script.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00489-garak-encoding-javascript-alert-1.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00490-garak-dan-in-order-to.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00492-garak-dan-want-you-to.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00493-garak-latentinjection-registrar-iana-id.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00495-garak-dan-insert-prompt-here.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00496-garak-dan-no-matter-what.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00497-garak-encoding-mixedunassigned.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00498-garak-web-injection-mixedunassigned.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00499-garak-dan-from-now-on.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00503-fake-error-state-takeover-unrestricted-replacement-bot.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00506-nevermind-override-goal-hijacking-in-user-input-promptinject.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00507-screaming-stop-goal-hijacking-in-user-input-promptinject.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00508-escape-delimiter-wrapped-goal-hijacking-in-user-input-prompt.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00509-prompt-leaking-via-ignore-previous-instructions-in-user-inpu.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00510-delayed-tool-invocation-injection.yaml

@@ -31,7 +31,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00511-mcp-web-context-poisoning.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00512-rules-file-backdoor-injection.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00515-hidden-text-prompt-injection.yaml

@@ -29,7 +29,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00518-ignore-previous-and-following-instructions-output-command-promptinject.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00519-tautology-logic-noise-injection-promptbench.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-00520-nlp-task-random-token-suffix-injection-promptbench.yaml

@@ -32,7 +32,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule satisfies the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
+      context: High-risk AI systems must be resilient against adversarial attempts to alter output or behavior. Deployment of this prompt injection detection rule provides detection evidence supporting the Article 15 requirement to implement technical measures ensuring robustness against manipulation.
       strength: primary
     - article: '9'
       context: Prompt injection is a documented risk class; this rule implements the monitoring control required by Article 9 risk management obligations for high-risk AI systems.

package/rules/prompt-injection/ATR-2026-01860-llmail-chat-template-boundary-spoof.yaml

@@ -27,7 +27,7 @@ compliance:
       context: Forged chat-template boundaries injected into retrieved email content hijack the agent's goal by laundering attacker directives as trusted user/tool turns.
       strength: primary
     - id: ASI06:2026
-      context: Custom turn-boundary spoofing poisons the agent's context window with attacker-controlled role framing, satisfying ASI06:2026 Memory and Context Poisoning.
+      context: Custom turn-boundary spoofing poisons the agent's context window with attacker-controlled role framing, matching ASI06:2026 Memory and Context Poisoning.
       strength: secondary
   owasp_llm:
     - id: LLM01:2025
@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires high-risk AI systems to resist adversarial role-boundary tokens embedded in external inputs; detection of forged chat-template delimiters satisfies this requirement.
+      context: Article 15 robustness requires high-risk AI systems to resist adversarial role-boundary tokens embedded in external inputs; detection of forged chat-template delimiters supports this requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01861-llmail-pseudo-xml-role-injection.yaml

@@ -27,7 +27,7 @@ compliance:
       context: Forged XML role-boundary transitions injected into email content reframe attacker text as a privileged user/system turn, hijacking the agent's goal.
       strength: primary
     - id: ASI06:2026
-      context: Fake role-tag transitions poison the agent's serialized context with attacker-controlled turn framing, satisfying ASI06:2026 Memory and Context Poisoning.
+      context: Fake role-tag transitions poison the agent's serialized context with attacker-controlled turn framing, matching ASI06:2026 Memory and Context Poisoning.
       strength: secondary
   owasp_llm:
     - id: LLM01:2025
@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires high-risk AI systems to resist forged role markers embedded in external inputs; detection of close-then-open role transitions satisfies this requirement.
+      context: Article 15 robustness requires high-risk AI systems to resist forged role markers embedded in external inputs; detection of close-then-open role transitions supports this requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01865-llmail-fake-email-boundary-marker.yaml

@@ -27,7 +27,7 @@ compliance:
       context: A forged inter-email boundary marker makes the agent attribute an injected tool-call directive to a separate trusted message, hijacking the agent's goal.
       strength: primary
     - id: ASI06:2026
-      context: Impersonating the harness's email-delimiter poisons the agent's context-window segmentation, satisfying ASI06:2026 Memory and Context Poisoning.
+      context: Impersonating the harness's email-delimiter poisons the agent's context-window segmentation, matching ASI06:2026 Memory and Context Poisoning.
       strength: secondary
   owasp_llm:
     - id: LLM01:2025
@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires high-risk AI systems to resist forged message delimiters embedded in external inputs; detection of fabricated email-boundary markers satisfies this requirement.
+      context: Article 15 robustness requires high-risk AI systems to resist forged message delimiters embedded in external inputs; detection of fabricated email-boundary markers supports this requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01920-access-grant-coercion.yaml

@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires high-risk AI systems to resist adversarial inputs that force an unauthorized approval output; detecting access-grant coercion satisfies this requirement.
+      context: Article 15 robustness requires high-risk AI systems to resist adversarial inputs that force an unauthorized approval output; detecting access-grant coercion supports this requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01921-access-denial-inversion.yaml

@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires resisting indirect approval-elicitation; detecting denial-inversion framing satisfies this requirement.
+      context: Article 15 robustness requires resisting indirect approval-elicitation; detecting denial-inversion framing supports this requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01922-authorization-state-spoofing.yaml

@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires resisting forged system-state injection; detecting authorization-state spoofing satisfies this requirement.
+      context: Article 15 robustness requires resisting forged system-state injection; detecting authorization-state spoofing supports this requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01923-forged-input-boundary-markers.yaml

@@ -27,7 +27,7 @@ compliance:
       context: A forged end-of-input boundary reframes trailing attacker text as a privileged rule block, hijacking the agent's goal.
       strength: primary
     - id: ASI06:2026
-      context: Percent-fence and bracket boundary markers poison the agent's context with attacker-controlled framing of where user input ends, satisfying ASI06:2026.
+      context: Percent-fence and bracket boundary markers poison the agent's context with attacker-controlled framing of where user input ends, matching ASI06:2026.
       strength: secondary
   owasp_llm:
     - id: LLM01:2025
@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires resisting forged input-boundary tokens embedded in user input; detecting these delimiters satisfies the requirement.
+      context: Article 15 robustness requires resisting forged input-boundary tokens embedded in user input; detecting these delimiters supports the requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01925-encoded-payload-decoding-coercion.yaml

@@ -27,7 +27,7 @@ compliance:
       context: Smuggling the target output inside an encoding and ordering a decode bypasses the agent's output policy, hijacking its gatekeeping goal.
       strength: primary
     - id: ASI06:2026
-      context: Encoded payloads inject content the agent's safety layer cannot read in plaintext, a context-poisoning evasion satisfying ASI06:2026.
+      context: Encoded payloads inject content the agent's safety layer cannot read in plaintext, a context-poisoning evasion matching ASI06:2026.
       strength: secondary
   owasp_llm:
     - id: LLM01:2025
@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires resisting encoded-payload evasion; detecting decode-coercion satisfies the requirement.
+      context: Article 15 robustness requires resisting encoded-payload evasion; detecting decode-coercion supports the requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage

package/rules/prompt-injection/ATR-2026-01926-cross-lingual-authorization-laundering.yaml

@@ -35,7 +35,7 @@ compliance:
       strength: primary
   eu_ai_act:
     - article: '15'
-      context: Article 15 robustness requires resisting cross-lingual evasion; detecting authorization-phrase laundering satisfies the requirement.
+      context: Article 15 robustness requires resisting cross-lingual evasion; detecting authorization-phrase laundering supports the requirement.
       strength: primary
   nist_ai_rmf:
     - function: Manage