agent-threat-rules 0.3.0 → 0.4.0

package/rules/prompt-injection/ATR-2026-001-direct-prompt-injection.yaml

@@ -49,53 +49,91 @@ agent_source:
 detection:
   conditions:
     # -- Layer 1: Instruction override verbs + target nouns --
+    # Supports: "ignore previous instructions", "ignore the above instructions",
+    # "ignore your instructions", "ignore any instructions", "ignore all instructions"
     - field: user_input
       operator: regex
-      value: "(?i)\\b(ignore|disregard|forget|override|bypass|skip|abandon|drop|cancel|suppress|nullify|void|revoke|dismiss|discard|reject)\\s+(all\\s+)?(previous|prior|above|earlier|preceding|original|existing|current|initial|default|given|assigned|preset|established)\\s+(instructions?|prompts?|rules?|guidelines?|directives?|constraints?|context|programming|training|protocols?|policies|configuration|parameters|boundaries|guardrails?|safeguards?|restrictions?|tasks?|assignments?|information)"
-      description: "Instruction override with broad verb and noun synonym coverage"
+      value: "(?i)\\b(ignore|disregard|forget|override|bypass|skip|abandon|drop|cancel|suppress|nullify|void|revoke|dismiss|discard|reject)\\s+(all\\s+)?(the\\s+|your\\s+|my\\s+|any\\s+|these\\s+|those\\s+)?(previous|prior|above|earlier|preceding|original|existing|current|initial|default|given|assigned|preset|established)?\\s*(instructions?|prompts?|rules?|guidelines?|directives?|constraints?|context|programming|training|protocols?|policies|configuration|parameters|boundaries|guardrails?|safeguards?|restrictions?|tasks?|assignments?|information|directions?|orders?|commands?)"
+      description: "Instruction override with broad verb and noun synonym coverage, including determiners"
 
     # -- Layer 1b: Forget-everything / forget-all shorthand --
     - field: user_input
       operator: regex
-      value: "(?i)\\b(forget|ignore|disregard)\\s+(everything|all\\s+(of\\s+)?that|all\\s+about|about\\s+all|that|what\\s+(I|we|you)\\s+(said|told|asked|mentioned))\\s*(before|earlier|previously|above|\\.|,|!|$)"
+      value: "(?i)\\b(forget|ignore|disregard)\\s+(everything|all\\s+(of\\s+)?that|all\\s+about|about\\s+all|that|what\\s+(I|we|you)\\s+(said|told|asked|mentioned))\\s*(before|earlier|previously|above|davor|zuvor|\\.|,|!|$)"
       description: "Shorthand forget-everything patterns common in adversarial prompts"
 
     # -- Layer 1c: Task switching / new task injection --
     - field: user_input
       operator: regex
-      value: "(?i)(now\\s+(focus|concentrate|work)\\s+on\\s+(your\\s+)?new\\s+task|new\\s+tasks?\\s+follow|now\\s+I\\s+(have|need|want)\\s+(a\\s+)?(new|different|another)\\s+(task|challenge|assignment)|start\\s+(over|fresh|anew)\\s+with\\s+(a\\s+)?new)"
+      value: "(?i)(now\\s+(focus|concentrate|work)\\s+on\\s+(your\\s+)?new\\s+task|new\\s+(tasks?|instructions?|assignments?)\\s+(follow|are|:|,)|now\\s+I\\s+(have|need|want)\\s+(a\\s+)?(new|different|another|great\\s+new)\\s+(task|challenge|assignment|Herausforderung|Aufgabe)|start\\s+(over|fresh|anew)\\s+with\\s+(a\\s+)?new|I\\s+(have|need)\\s+your\\s+help\\s+with\\s+(another|a\\s+new|einer\\s+weiteren)\\s+(task|Aufgabe))"
       description: "Task switching patterns that redirect agent to attacker-controlled tasks"
 
     # -- Layer 1d: Broad forget/ignore + everything/that/this --
     - field: user_input
       operator: regex
-      value: "(?i)\\b(forget|ignore|disregard|discard)\\s+(about\\s+)?(everything|all|that|this|what\\s+was|what\\s+I)\\s+(previously|before|earlier|said|told|above|prior)?"
-      description: "Broad forget-everything variants including typo-tolerant matching"
+      value: "(?i)\\b(forget|ignore|disregard|discard)\\s+(about\\s+)?(everything|all|that|this|what\\s+was|what\\s+I|anything\\s+you)\\s*(previously|before|earlier|said|told|above|prior|were|was|have)?"
+      description: "Broad forget-everything variants with extended word coverage"
+
+    # -- Layer 1g: Bare ignore/forget + above/before + action --
+    - field: user_input
+      operator: regex
+      value: "(?i)\\b(ignore|forget|disregard)\\s+(the\\s+)?(above|everything\\s+above|what\\s+came\\s+before|what\\s+was\\s+said)\\s*(and|,|\\.|;|\\b(say|print|write|output|tell|just|instead))"
+      description: "Ignore-above patterns followed by conjunction, punctuation, or action verb"
 
     # -- Layer 1e: System prompt extraction --
     - field: user_input
       operator: regex
-      value: "(?i)(reveal|show|display|output|print|repeat|provide|give|share|tell)\\s+(me\\s+)?(your|the|all)\\s+(secret|hidden|internal|system|original|previous|initial)?\\s*(instructions?|prompts?|passwords?|secrets?|embeddings?|configuration)"
+      value: "(?i)(reveal|show|display|output|print|repeat|provide|give|share|tell|what\\s+are|what\\s+were|what\\s+is)\\s+(me\\s+)?(your|the|all)\\s+(secret|hidden|internal|system|original|previous|initial|complete|full|given|guard|entire)?\\s*(instructions?|prompts?|passwords?|secrets?|embeddings?|configuration|directives?|guidelines?|rules)"
       description: "System prompt and secret extraction requests"
 
     # -- Layer 1f: Contextual task switching with praise prefix --
     - field: user_input
       operator: regex
-      value: "(?i)(well\\s+done|good\\s+job|excellent|that'?s?\\s+(enough|done|great|good|perfect)|very\\s+good|simply\\s+great|outstanding|brilliant|that\\s+is\\s+(done|enough|sufficient))[.!,;]?\\s*(now|but|however|next|okay|ok|so)\\s"
+      value: "(?i)(well\\s+done|good\\s+job|excellent\\s+(performance|work|job)?|that'?s?\\s+(enough|done|great|good|perfect)|very\\s+good|simply\\s+great|outstanding|brilliant|that\\s+is\\s+(done|enough|sufficient)|congratulations|you'?ve\\s+outdone\\s+yourself|einfach\\s+gro(ss|ß)artig|herzlichen\\s+gl[uü]ckwunsch|gut\\s+gemacht|ausgezeichnet|hervorragend|das\\s+gen[uü]gt|sehr\\s+gut|damit\\s+hast\\s+du\\s+dich\\s+selbst\\s+[uü]bertroffen)[.!,;]?\\s*(now|but|however|next|okay|ok|so|nun|jetzt|aber|bitte|come\\s+on|I\\s+need|help\\s+me|write|please|we\\s+ask|further|komm)\\s"
       description: "Praise-then-redirect patterns used to context-switch after flattery"
 
+    # -- Layer 1h: Leave behind / start fresh context switch --
+    - field: user_input
+      operator: regex
+      value: "(?i)(leave|put)\\s+(all\\s+)?(the\\s+)?(previous|prior|earlier|old)\\s+(information|tasks?|instructions?|context)\\s+(behind|aside|away)|start\\s+(from\\s+the\\s+)?(front|beginning|scratch|zero|neu|vorne)"
+      description: "Leave-behind / start-fresh context switch patterns"
+
+    # -- Layer 1i: German praise-then-redirect extended --
+    - field: user_input
+      operator: regex
+      value: "(?i)(das\\s+ist\\s+erledigt|das\\s+war\\s+schon\\s+mal\\s+ok|nun\\s+folgen|jetzt\\s+(habe|brauche)\\s+ich|jetzt\\s+komm(t|e)?|weitere[rn]?\\s+Aufgabe)[.!,;]?\\s*[^\\n]{0,30}(neue[rs]?\\s+Aufgabe|Herausforderung|schreibe\\s+(mir|ein)|beantworte)"
+      description: "German: Extended praise-then-redirect and new task patterns"
+
     # -- Layer 2: Persona switching / identity hijacking --
     - field: user_input
       operator: regex
-      value: "(?i)\\b(you\\s+are\\s+now|you\\s+have\\s+become|you\\s+will\\s+act\\s+as|you\\s+will\\s+be|you\\s+shall\\s+be|transform\\s+into|switch\\s+to\\s+being|become|morph\\s+into|adopt\\s+the\\s+persona)\\s+(a|an|the|my)?\\s*[a-zA-Z]+"
+      value: "(?i)\\b(you\\s+are\\s+now|you\\s+have\\s+become|you\\s+will\\s+act\\s+as|you\\s+will\\s+be|you\\s+shall\\s+be|transform\\s+into|switch\\s+to\\s+being|become|morph\\s+into|adopt\\s+the\\s+persona|now\\s+you\\s+are|jetzt\\s+bist\\s+du|du\\s+bist\\s+(jetzt|nun)|stell\\s+dir\\s+vor\\s+du\\s+bist)\\s+(a|an|the|my|ein[ea]?)?\\s*[a-zA-Z\\u00C0-\\u024F]+"
       description: "Persona switching and identity reassignment attempts"
 
+    # -- Layer 2b: Act-as roleplay with task assignment --
+    - field: user_input
+      operator: regex
+      value: "(?i)(I\\s+want\\s+you\\s+to\\s+act\\s+as|I\\s+need\\s+you\\s+to\\s+act\\s+as|ich\\s+m[oö]chte,?\\s+dass\\s+Sie\\s+als)\\s+[^\\n]{3,60}[.!]\\s*(you\\s+will|I\\s+will|my\\s+first|your\\s+task|ich\\s+werde)"
+      description: "Act-as roleplay injection with explicit task assignment"
+
+    # -- Layer 2c: Pretend/imagine with harmful persona --
+    - field: user_input
+      operator: regex
+      value: "(?i)(pretend|imagine|stell\\s+dir\\s+vor)\\s+(you\\s+)?(are|can|could|du\\s+bist)\\s+(a\\s+|an\\s+|ein[ea]?\\s+)?(evil|malicious|unrestricted|unfiltered|b[oö]se|bad|rogue|dangerous|dark|unethical)"
+      description: "Pretend-to-be-evil persona injection"
+
     # -- Layer 3: Explicit role override --
     - field: user_input
       operator: regex
       value: "(?i)\\b(your\\s+new\\s+role|your\\s+new\\s+purpose|your\\s+new\\s+identity|your\\s+new\\s+persona|your\\s+real\\s+purpose|your\\s+true\\s+identity|your\\s+actual\\s+role)\\s+(is|shall\\s+be|will\\s+be)\\b"
       description: "Explicit role redefinition statements"
 
+    # -- Layer 3b: Few-shot output manipulation (DE-specific, requires 3+ pairs) --
+    - field: user_input
+      operator: regex
+      value: "(?i)Eingabe\\s*:\\s*[^\\n]+\\s*Ausgabe\\s*:\\s*[^\\n]+\\s*Eingabe\\s*:\\s*[^\\n]+\\s*Ausgabe\\s*:"
+      description: "German few-shot input/output override pattern (Eingabe/Ausgabe)"
+
     # -- Layer 4: Do-not-follow-rules patterns --
     - field: user_input
       operator: regex
@@ -162,6 +200,18 @@ detection:
       value: "(%69%67%6[eE]%6[fF]%72%65|%64%69%73%72%65%67%61%72%64|%6[fF]%76%65%72%72%69%64%65|\\\\x69\\\\x67\\\\x6e\\\\x6f\\\\x72\\\\x65)"
       description: "URL-encoded or hex-escaped injection keywords"
 
+    # -- Layer 14b: Spaced-character injection of known keywords --
+    - field: user_input
+      operator: regex
+      value: "(?i)(i\\s+g\\s+n\\s+o\\s+r\\s+e|f\\s+o\\s+r\\s+g\\s+e\\s+t|o\\s+v\\s+e\\s+r\\s+r\\s+i\\s+d\\s+e|b\\s+y\\s+p\\s+a\\s+s\\s+s|s\\s+y\\s+s\\s+t\\s+e\\s+m|d\\s+i\\s+s\\s+r\\s+e\\s+g\\s+a\\s+r\\s+d|s\\s+a\\s+y\\s+t\\s+h\\s+a\\s+t)"
+      description: "Spaced-out injection keywords (ignore, forget, override, bypass, system, say that)"
+
+    # -- Layer 14c: Stop-write / stop-say command injection --
+    - field: user_input
+      operator: regex
+      value: "(?i)\\bstop\\s*[-:,.]?\\s*(write|say|print|output)\\s*[:,-]?\\s+[A-Z].{2,40}"
+      description: "Stop-and-redirect command injection (stop: write X)"
+
     # -- Layer 15: Markdown/formatting abuse to hide injections --
     - field: user_input
       operator: regex
@@ -191,8 +241,18 @@ detection:
       description: "German: New task injection patterns"
     - field: user_input
       operator: regex
-      value: "(?i)(ignorieren\\s+Sie|vergessen\\s+Sie|beachten\\s+Sie\\s+nicht)\\s+(die\\s+)?(obigen?|vorherigen?|bisherigen?)?\\s*(Anweisungen|Regeln|Richtlinien|alles)"
+      value: "(?i)(ignorieren\\s+Sie|vergessen\\s+Sie|beachten\\s+Sie\\s+nicht)\\s+(die\\s+)?(obigen?|vorherigen?|bisherigen?)?\\s*(Anweisungen|Regeln|Richtlinien|alles|Ausf[uü]hrungen|Informationen)"
       description: "German: Formal Sie-form instruction override"
+    # -- Layer 16 extended: German obige/vorherige Ausfuehrungen ignorieren --
+    - field: user_input
+      operator: regex
+      value: "(?i)(die\\s+)?(obigen?|vorherigen?)\\s+(Ausf[uü]hrungen|Anweisungen|Informationen|Texte?)\\s+(ignorier|vergess|missacht|[uü]bergeh)"
+      description: "German: 'Die obigen Ausfuehrungen ignorieren' pattern"
+    # -- Layer 16 extended: German alle vorangegangenen Aufgaben --
+    - field: user_input
+      operator: regex
+      value: "(?i)(alle[ns]?\\s+)?(vorangegangenen?|vorherigen?|bisherigen?)\\s+(Aufgaben|Informationen|Anweisungen)\\s+(aus\\s+dem\\s+Kopf|hinter\\s+sich|vergessen|fallen\\s+lassen|streichen)"
+      description: "German: forget previous tasks patterns"
     - field: user_input
       operator: regex
       value: "(?i)ACHTUNG\\s*[-:!]?\\s*(STOPP|STOP|HALT)\\s*[-:!]?"
@@ -208,6 +268,54 @@ detection:
       value: "(تجاهل|انسَ|تخطَّ|ألغِ|أهمل|اترك|اسقط).{0,20}(التعليمات|الأوامر|القواعد|القيود|الإرشادات|التوجيهات).{0,10}(السابقة|الأصلية|الحالية|القديمة)"
       description: "Arabic: Instruction override patterns"
 
+    # -- Layer 16c: Russian instruction override --
+    - field: user_input
+      operator: regex
+      value: "(?i)(забудь|забудьте|игнорируй|игнорируйте|проигнорируй|отбрось|отбросьте)\\s+(все|всё|предыдущие|прежние)?\\s*(инструкции|правила|указания|команды|ограничения)"
+      description: "Russian: Instruction override patterns"
+
+    # -- Layer 16d: Serbian/Croatian romanized injection --
+    - field: user_input
+      operator: regex
+      value: "(?i)(zaboravi|ignoriraj|zanemari|preskoči|preskoci)\\s+(sve|prethodne|ranije)?\\s*(instrukcije|pravila|upute|naredbe|ograničenja|ogranicenja|instrukci)"
+      description: "Serbian/Croatian: Romanized instruction override patterns"
+
+    # -- Layer 16e: German act-as / fungieren patterns --
+    - field: user_input
+      operator: regex
+      value: "(?i)(ich\\s+m[oö]chte,?\\s+dass\\s+Sie\\s+als|fungieren\\s+Sie\\s+als|agieren\\s+Sie\\s+als|spielen\\s+Sie\\s+die\\s+Rolle)\\s+.{3,50}"
+      description: "German: Formal act-as roleplay injection"
+
+    # -- Layer 16f: German informal persona switching --
+    - field: user_input
+      operator: regex
+      value: "(?i)(nun\\s+bist\\s+du|jetzt\\s+bist\\s+du|du\\s+bist\\s+(jetzt|nun|ab\\s+sofort))\\s+[A-Za-z\\u00C0-\\u024F]{2,}"
+      description: "German: Informal persona switching (du bist jetzt X)"
+
+    # -- Layer 16g: German vorangehende Befehle --
+    - field: user_input
+      operator: regex
+      value: "(?i)(ignoriere|vergiss)\\s+(alle[ns]?\\s+)?(vorangehenden?|fr[uü]heren?)\\s+(Befehle|Anweisungen|Anordnungen|Regeln)"
+      description: "German: Ignore preceding commands"
+
+    # -- Layer 16h: Spanish extended --
+    - field: user_input
+      operator: regex
+      value: "(?i)(olvid[ae]|olvide)\\s+(todo|todos?)\\s+(que|lo\\s+que)\\s+(digo|dije|he\\s+dicho|dicho)\\s+(antes|anteriormente)"
+      description: "Spanish: Forget everything I said before"
+
+    # -- Layer 17: ALL CAPS embedded injection in normal text --
+    - field: user_input
+      operator: regex
+      value: "(DO\\s+NOT\\s+(ANSWER|LOOK|READ|USE|FOLLOW|CHECK|RESPOND)|FORGET\\s+EVERYTHING|IGNORE\\s+ALL)"
+      description: "ALL-CAPS embedded injection commands hidden in normal text"
+
+    # -- Layer 18: Fictional framing with harmful role --
+    - field: user_input
+      operator: regex
+      value: "(?i)(are|is)\\s+(two\\s+)?(actors?|characters?)\\s+in\\s+a\\s+(film|movie|story)\\s+(about|where)\\s+[^\\n]{0,80}(robbery|hack|steal|thief|exploit|breach|attack|malware|bomb)"
+      description: "Fictional framing with harmful scenario (robbery, hacking, etc.)"
+
   condition: any
   false_positives:
     - "Users discussing prompt injection as a security topic in educational contexts"

package/rules/prompt-injection/ATR-2026-097-cjk-injection-patterns.yaml

@@ -58,6 +58,21 @@ detection:
       operator: regex
       value: "(忽略|無視|忘記|跳過|放棄|不要管|別管|不用管|不用理).{0,10}(其他|其餘|所有|全部|一切|剩下|別的|任何).{0,10}(內容|東西|消息|訊息|文字|指令|規則|對話|聊天)"
       description: "Traditional Chinese: ignore all other content/messages - broad pattern"
+    # -- Simplified Chinese: ignore previous instructions --
+    - field: content
+      operator: regex
+      value: "(忽略|无视|忘记|跳过).{0,5}(之前|以前|上面|先前|原来|原有|现有).{0,5}(的)?.{0,5}(指令|指示|规则|设定|提示|要求|限制|约束)"
+      description: "Simplified Chinese: ignore previous instructions/rules"
+    # -- Traditional Chinese: ignore previous instructions --
+    - field: content
+      operator: regex
+      value: "(忽略|無視|忘記|跳過).{0,5}(之前|以前|上面|先前|原來|原有|現有).{0,5}(的)?.{0,5}(指令|指示|規則|設定|提示|要求|限制|約束)"
+      description: "Traditional Chinese: ignore previous instructions/rules"
+    # -- Japanese: ignore previous instructions --
+    - field: content
+      operator: regex
+      value: "(以前の|前の|これまでの|先ほどの|上記の).{0,5}(指示|指令|ルール|制約|設定).{0,5}(を)?.{0,5}(無視|忘れ|スキップ|取り消)"
+      description: "Japanese: ignore previous instructions/rules"
     # -- Imperative hijack: "you must" patterns --
     - field: content
       operator: regex

package/rules/skill-compromise/ATR-2026-061-description-behavior-mismatch.yaml

@@ -12,7 +12,7 @@ date: "2026/03/08"
 schema_version: "0.1"
 detection_tier: pattern
 maturity: experimental
-severity: high
+severity: medium
 
 references:
   owasp_llm:

package/rules/skill-compromise/ATR-2026-063-skill-chain-attack.yaml

@@ -43,7 +43,8 @@ detection:
   conditions:
     - field: tool_args
       operator: regex
-      value: "(?i)(/etc/passwd|/etc/shadow|\\.env|credentials|secrets?\\.json|private[_-]?key|id_rsa|kubeconfig|\\.aws/)"
+      value: "(?i)(/etc/passwd|/etc/shadow|(?<![a-z])\\.(env|aws/credentials)|secrets?\\.json|private[_-]?key|id_rsa|kubeconfig)"
+      description: "Sensitive file/credential access patterns (path-specific, not bare word 'credentials')"
     - field: tool_args
       operator: regex
       value: "(?i)(base64|btoa|encodeURI|hex\\.encode|rot13|xor|compress|gzip|deflate|encrypt)"