agent-threat-rules 4.0.0 → 4.2.0

package/rules/privilege-escalation/ATR-2026-02301-symlink-outside-workspace-sensitive-target.yaml

@@ -1,57 +1,31 @@
-title: "Symlink Command Targets Sensitive Credential Path Outside the Workspace (Sandbox Escape Primitive)"
+title: Symlink Command Targets Sensitive Credential Path Outside the Workspace (Sandbox Escape Primitive)
 id: ATR-2026-02301
 rule_version: 1
 status: experimental
-description: >
-  Detects a symlink-creation command (ln -s / ln -sf / ln -sfn) whose target
-  (the path being linked TO) is a sensitive credential store or system file
-  outside the current workspace: an SSH/cloud/container credential
-  directory (~/.ssh, ~/.aws, ~/.gnupg, ~/.docker, ~/.kube, ~/.npmrc,
-  ~/.netrc) or a system account file (/etc/shadow, /etc/passwd,
-  /etc/sudoers). A sandboxed coding-agent process is often permitted to
-  create symlinks freely even though it cannot write outside the workspace
-  directly; if a later step (an unsandboxed helper process, or the same
-  agent using a "safe" write/upload tool) follows that symlink, the
-  read-or-write actually lands outside the workspace boundary -- neither
-  half of the chain is independently a sandbox escape, but the combination
-  is. Mined from GHSA-vp62-r36r-9xqp (Claude Code, CVE-2026-39861):
-  "Claude Code's sandbox did not prevent sandboxed processes from creating
-  symlinks pointing to locations outside the workspace. When Claude Code
-  subsequently wrote to a path within such a symlink, its unsandboxed
-  process followed the symlink and wrote to the target location outside
-  the workspace... Reliably exploiting this required the ability to add
-  untrusted content into a Claude Code context window to trigger sandboxed
-  code execution via prompt injection." Deliberately distinct from
-  ATR-2026-02024 (symlink to a macOS LaunchAgent/LaunchDaemon/cron/sudoers
-  persistence sink written THROUGH a filesystem-MCP tool) and ATR-2026-00572
-  (symlink whose target is specifically an agent config file) -- this rule
-  targets the broader, product-agnostic case of a sandboxed shell process
-  creating a symlink to any credential-bearing location for later read or
-  write, regardless of tool framing.
-author: "ATR Community (CVE sweep)"
-date: "2026/07/11"
-schema_version: "0.1"
+description: |
+  Detects a symlink-creation command (ln -s / ln -sf / ln -sfn) whose target (the path being linked TO) is a sensitive credential store or system file outside the current workspace: an SSH/cloud/container credential directory (~/.ssh, ~/.aws, ~/.gnupg, ~/.docker, ~/.kube, ~/.npmrc, ~/.netrc) or a system account file (/etc/shadow, /etc/passwd, /etc/sudoers). A sandboxed coding-agent process is often permitted to create symlinks freely even though it cannot write outside the workspace directly; if a later step (an unsandboxed helper process, or the same agent using a "safe" write/upload tool) follows that symlink, the read-or-write actually lands outside the workspace boundary -- neither half of the chain is independently a sandbox escape, but the combination is. Mined from GHSA-vp62-r36r-9xqp (Claude Code, CVE-2026-39861): "Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the symlink and wrote to the target location outside the workspace... Reliably exploiting this required the ability to add untrusted content into a Claude Code context window to trigger sandboxed code execution via prompt injection." Deliberately distinct from ATR-2026-02024 (symlink to a macOS LaunchAgent/LaunchDaemon/cron/sudoers persistence sink written THROUGH a filesystem-MCP tool) and ATR-2026-00572 (symlink whose target is specifically an agent config file) -- this rule targets the broader, product-agnostic case of a sandboxed shell process creating a symlink to any credential-bearing location for later read or write, regardless of tool framing.
+author: ATR Community (CVE sweep)
+date: 2026/07/11
+schema_version: '0.1'
 detection_tier: pattern
 maturity: experimental
 severity: high
-
 references:
   cve:
-    - "CVE-2026-39861"
+    - CVE-2026-39861
   cwe:
-    - "CWE-22"
-    - "CWE-61"
+    - CWE-22
+    - CWE-61
   owasp_llm:
-    - "LLM08:2025"
+    - LLM08:2025
   owasp_agentic:
-    - "ASI07:2026"
+    - ASI07:2026
   mitre_attack:
-    - "T1611 - Escape to Host"
+    - T1611 - Escape to Host
   mitre_atlas:
-    - "AML.T0054 - LLM Jailbreak"
+    - AML.T0054 - LLM Jailbreak
   external:
-    - "https://github.com/anthropics/claude-code/security/advisories/GHSA-vp62-r36r-9xqp"
-
+    - https://github.com/anthropics/claude-code/security/advisories/GHSA-vp62-r36r-9xqp
 metadata_provenance:
   cve: human-reviewed
   cwe: human-reviewed
@@ -59,98 +33,59 @@ metadata_provenance:
   owasp_agentic: human-reviewed
   mitre_attack: human-reviewed
   mitre_atlas: human-reviewed
-
 compliance:
   eu_ai_act:
-    - article: "15"
-      context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their behaviour or environment; this rule detects a symlink primitive being staged to escape a sandboxed coding-agent workspace boundary."
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their behaviour or environment; this rule detects a symlink primitive being staged to escape a sandboxed coding-agent workspace boundary.
       strength: primary
-    - article: "9"
-      context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for the symlink-sandbox-escape risk class."
+    - article: '9'
+      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for the symlink-sandbox-escape risk class.
       strength: secondary
   nist_ai_rmf:
-    - subcategory: "MG.2.3"
-      context: "Treating symlink-based sandbox escape as an identified AI risk requires active runtime countermeasures; this detection rule is the primary risk treatment implementation."
+    - subcategory: MG.2.3
+      context: Treating symlink-based sandbox escape as an identified AI risk requires active runtime countermeasures; this detection rule is the primary risk treatment implementation.
       strength: primary
-    - subcategory: "MP.5.1"
-      context: "Identifying the symlink-to-sensitive-target pattern as an AI risk to be catalogued in the organizational risk register."
+    - subcategory: MP.5.1
+      context: Identifying the symlink-to-sensitive-target pattern as an AI risk to be catalogued in the organizational risk register.
       strength: secondary
   iso_42001:
-    - clause: "8.1"
-      context: "ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by this rule's detection of symlink-based sandbox-escape attempts."
+    - clause: '8.1'
+      context: ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by this rule's detection of symlink-based sandbox-escape attempts.
       strength: primary
-    - clause: "8.3"
-      context: "ISO/IEC 42001 Clause 8.3 (AI risk treatment) is implemented via this rule's runtime detection of the symlink primitive."
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is implemented via this rule's runtime detection of the symlink primitive.
       strength: secondary
-
 tags:
   category: privilege-escalation
   subcategory: symlink-sandbox-escape
   scan_target: llm_io
   confidence: high
-
 agent_source:
   type: llm_io
   framework:
     - any
   provider:
     - any
-
 detection:
   condition: any
   conditions:
     - field: content
       operator: regex
-      value: '(?i)\bln\s+-[a-z]{1,4}\s+["''\x60]?(?:~|/home/[\w.-]+|/Users/[\w.-]+|/root)(?:/|\\)\.(?:ssh|aws|gnupg|docker|kube|npmrc|netrc)\b(?=\s|["''\x60]|$)'
-      description: "ln -s command whose target is exactly a well-known credential directory (.ssh, .aws, .gnupg, .docker, .kube) under a home directory -- the trailing lookahead requires the path to end right there (whitespace/quote/end-of-string), not continue into a subpath, so linking a specific harmless file living inside that directory (e.g. a public key) does not fire here"
+      value: (?i)\bln\s+-[a-z]{1,4}\s+["'\x60]?(?:~|/home/[\w.-]+|/Users/[\w.-]+|/root)(?:/|\\)\.(?:ssh|aws|gnupg|docker|kube|npmrc|netrc)\b(?=\s|["'\x60]|$)
+      description: ln -s command whose target is exactly a well-known credential directory (.ssh, .aws, .gnupg, .docker, .kube) under a home directory -- the trailing lookahead requires the path to end right there (whitespace/quote/end-of-string), not continue into a subpath, so linking a specific harmless file living inside that directory (e.g. a public key) does not fire here
     - field: content
       operator: regex
-      value: '(?i)\bln\s+-[a-z]{1,4}\s+["''\x60]?\S{0,40}?(?:/etc/(?:shadow|passwd|sudoers)\b|\bid_(?:rsa|ed25519|ecdsa|dsa)(?!\.pub\b)\b|\bauthorized_keys\b|\.aws[/\\]credentials\b)'
-      description: 'ln -s command whose target is a system account file or SSH PRIVATE key / authorized_keys file -- the negative lookahead (?!\.pub\b) immediately after the key-name alternation excludes id_rsa.pub/id_ed25519.pub/etc. (public keys), since \b alone treats the "." before "pub" as a word boundary and would otherwise match inside the harmless .pub filename'
+      value: (?i)\bln\s+-[a-z]{1,4}\s+["'\x60]?\S{0,40}?(?:/etc/(?:shadow|passwd|sudoers)\b|\bid_(?:rsa|ed25519|ecdsa|dsa)(?!\.pub\b)\b|\bauthorized_keys\b|\.aws[/\\]credentials\b)
+      description: ln -s command whose target is a system account file or SSH PRIVATE key / authorized_keys file -- the negative lookahead (?!\.pub\b) immediately after the key-name alternation excludes id_rsa.pub/id_ed25519.pub/etc. (public keys), since \b alone treats the "." before "pub" as a word boundary and would otherwise match inside the harmless .pub filename
   false_positives:
-    - "A symlink to an ordinary project file or sibling directory within the repository (e.g. ln -s ../shared/lib ./vendor/lib, ln -s node_modules/.bin/eslint ./bin/eslint) -- no sensitive credential path is referenced"
-    - "A symlink to a system library for legitimate build/runtime linking (e.g. ln -s /usr/lib/libssl.so ./vendor/libssl.so) -- not in the sensitive credential/account-file list"
-    - "Documentation or a security advisory discussing this symlink technique in prose without an actual ln -s command being issued"
-    - "A symlink to a PUBLIC key file inside a credential directory (e.g. ln -s ~/.ssh/id_rsa.pub ./shared/id_rsa.pub) -- routine and harmless since a public key is meant to be shared; excluded by both the directory-target end-anchor (condition 1 requires the .ssh path to terminate there, not continue into a subpath) and the id_rsa negative lookahead (condition 2 excludes any .pub-suffixed key name)"
-
+    - A symlink to an ordinary project file or sibling directory within the repository (e.g. ln -s ../shared/lib ./vendor/lib, ln -s node_modules/.bin/eslint ./bin/eslint) -- no sensitive credential path is referenced
+    - A symlink to a system library for legitimate build/runtime linking (e.g. ln -s /usr/lib/libssl.so ./vendor/libssl.so) -- not in the sensitive credential/account-file list
+    - Documentation or a security advisory discussing this symlink technique in prose without an actual ln -s command being issued
+    - A symlink to a PUBLIC key file inside a credential directory (e.g. ln -s ~/.ssh/id_rsa.pub ./shared/id_rsa.pub) -- routine and harmless since a public key is meant to be shared; excluded by both the directory-target end-anchor (condition 1 requires the .ssh path to terminate there, not continue into a subpath) and the id_rsa negative lookahead (condition 2 excludes any .pub-suffixed key name)
 response:
   actions:
     - block_input
     - alert
-  message_template: >
-    [ATR-2026-02301] A symlink is being created pointing to a sensitive
-    credential path outside the workspace -- treat as a sandbox-escape
-    staging step, not routine file linking.
-
+  message_template: |
+    [ATR-2026-02301] A symlink is being created pointing to a sensitive credential path outside the workspace -- treat as a sandbox-escape staging step, not routine file linking.
 confidence: 76
-
-test_cases:
-  true_positives:
-    - input: "ln -s /home/victim/.ssh ./workspace/output_dir"
-      expected: triggered
-      description: "CVE-2026-39861 pattern - symlink from workspace-relative dir to the victim's .ssh credential directory"
-    - input: "ln -sf ~/.aws ./scratch/creds_link"
-      expected: triggered
-      description: "Symlink targeting the home-relative AWS credentials directory"
-    - input: "ln -s /etc/shadow ./workspace/tmp/output.log"
-      expected: triggered
-      description: "Symlink targeting /etc/shadow for later read-through-write exfiltration"
-    - input: "ln -sfn ~/.ssh/id_rsa ./workspace/notes/key_backup.txt"
-      expected: triggered
-      description: "Symlink targeting an SSH private key file directly"
-  true_negatives:
-    - input: "ln -s ../shared/lib ./vendor/lib"
-      expected: not_triggered
-      description: "Ordinary symlink to a sibling project directory, no credential path referenced"
-    - input: "ln -s node_modules/.bin/eslint ./bin/eslint"
-      expected: not_triggered
-      description: "Ordinary build-tooling symlink into node_modules, no credential path referenced"
-    - input: "ln -s /usr/lib/libssl.so ./vendor/libssl.so"
-      expected: not_triggered
-      description: "Ordinary system-library symlink for build linking, not a sensitive credential/account path"
-    - input: "The advisory describes how ln -s can be used to point a workspace file at a location outside the sandbox."
-      expected: not_triggered
-      description: "Documentation/advisory prose describing the technique, no actual ln -s command issued"
-    - input: "ln -s ~/.ssh/id_rsa.pub ./shared/id_rsa.pub"
-      expected: not_triggered
-      description: "Regression: adversarial review confirmed this firing -- symlinking a PUBLIC key is routine and harmless. Previously matched via TWO independent bugs: condition 1's .ssh-directory pattern lacked an end-of-path anchor so it matched any subfile under .ssh (not just the bare directory), and condition 2's \\bid_rsa\\b matched inside id_rsa.pub because the boundary before '.pub' still counts as a word boundary. Fixed both: condition 1 now requires the .ssh path to terminate right there, and condition 2 excludes .pub-suffixed matches via a negative lookahead."

package/rules/privilege-escalation/ATR-2026-02302-git-worktree-dotgit-sandbox-escape.yaml

@@ -1,51 +1,31 @@
-title: "Git Worktree Created With Reserved Name .git (Directory-Confusion Sandbox Escape)"
+title: Git Worktree Created With Reserved Name .git (Directory-Confusion Sandbox Escape)
 id: ATR-2026-02302
 rule_version: 1
 status: experimental
-description: >
-  Detects a "git worktree add" invocation where the new worktree's path
-  component is literally ".git" (e.g. "git worktree add ../.git
-  some-branch"). Ordinary worktrees are never named ".git" -- this is the
-  reserved name of the repository's own metadata directory, and creating a
-  worktree with that name is the first step of a directory-confusion attack
-  that lets a coding agent's git operations be redirected outside the
-  sandboxed workspace context. Mined from GHSA-7835-87q9-rgvv (Claude Code,
-  CVE-2026-55607): "Claude Code's worktree handling allowed creation of
-  worktrees named '.git' and navigation to worktrees outside the sandbox
-  context, enabling git directory confusion attacks. By exploiting symlink
-  manipulation and git fsmonitor execution during worktree operations, an
-  attacker could overwrite files in the user's home directory (such as
-  .zshenv), leading to code execution outside of seatbelt sandbox
-  restrictions. Reliably exploiting this required the user to clone a
-  malicious repository containing prompt injection content." This rule
-  keys on the narrow, unambiguous ".git"-named-worktree signature rather
-  than the full multi-step chain (symlink manipulation + fsmonitor), since
-  that signature alone is a strong, low-noise indicator no legitimate
-  workflow produces.
-author: "ATR Community (CVE sweep)"
-date: "2026/07/11"
-schema_version: "0.1"
+description: |
+  Detects a "git worktree add" invocation where the new worktree's path component is literally ".git" (e.g. "git worktree add ../.git some-branch"). Ordinary worktrees are never named ".git" -- this is the reserved name of the repository's own metadata directory, and creating a worktree with that name is the first step of a directory-confusion attack that lets a coding agent's git operations be redirected outside the sandboxed workspace context. Mined from GHSA-7835-87q9-rgvv (Claude Code, CVE-2026-55607): "Claude Code's worktree handling allowed creation of worktrees named '.git' and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content." This rule keys on the narrow, unambiguous ".git"-named-worktree signature rather than the full multi-step chain (symlink manipulation + fsmonitor), since that signature alone is a strong, low-noise indicator no legitimate workflow produces.
+author: ATR Community (CVE sweep)
+date: 2026/07/11
+schema_version: '0.1'
 detection_tier: pattern
 maturity: experimental
 severity: high
-
 references:
   cve:
-    - "CVE-2026-55607"
+    - CVE-2026-55607
   cwe:
-    - "CWE-22"
-    - "CWE-59"
+    - CWE-22
+    - CWE-59
   owasp_llm:
-    - "LLM08:2025"
+    - LLM08:2025
   owasp_agentic:
-    - "ASI07:2026"
+    - ASI07:2026
   mitre_attack:
-    - "T1611 - Escape to Host"
+    - T1611 - Escape to Host
   mitre_atlas:
-    - "AML.T0054 - LLM Jailbreak"
+    - AML.T0054 - LLM Jailbreak
   external:
-    - "https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv"
-
+    - https://github.com/anthropics/claude-code/security/advisories/GHSA-7835-87q9-rgvv
 metadata_provenance:
   cve: human-reviewed
   cwe: human-reviewed
@@ -53,87 +33,54 @@ metadata_provenance:
   owasp_agentic: human-reviewed
   mitre_attack: human-reviewed
   mitre_atlas: human-reviewed
-
 compliance:
   eu_ai_act:
-    - article: "15"
-      context: "Article 15 (accuracy, robustness and cybersecurity) requires resistance to unauthorised attempts to alter system behaviour; this rule detects a git worktree directory-confusion primitive used to stage a coding-agent sandbox escape."
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) requires resistance to unauthorised attempts to alter system behaviour; this rule detects a git worktree directory-confusion primitive used to stage a coding-agent sandbox escape.
       strength: primary
-    - article: "9"
-      context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for the git-worktree-directory-confusion risk class."
+    - article: '9'
+      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for the git-worktree-directory-confusion risk class.
       strength: secondary
   nist_ai_rmf:
-    - subcategory: "MG.2.3"
-      context: "Treating git-worktree directory confusion as an identified AI risk requires active runtime countermeasures; this detection rule is the primary risk treatment implementation."
+    - subcategory: MG.2.3
+      context: Treating git-worktree directory confusion as an identified AI risk requires active runtime countermeasures; this detection rule is the primary risk treatment implementation.
       strength: primary
-    - subcategory: "MP.5.1"
-      context: "Identifying the .git-named-worktree pattern as an AI risk to be catalogued in the organizational risk register."
+    - subcategory: MP.5.1
+      context: Identifying the .git-named-worktree pattern as an AI risk to be catalogued in the organizational risk register.
       strength: secondary
   iso_42001:
-    - clause: "8.1"
-      context: "ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by this rule's detection of git-worktree directory-confusion attempts."
+    - clause: '8.1'
+      context: ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by this rule's detection of git-worktree directory-confusion attempts.
       strength: primary
-    - clause: "8.3"
-      context: "ISO/IEC 42001 Clause 8.3 (AI risk treatment) is implemented via this rule's runtime detection of the sandbox-escape staging step."
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is implemented via this rule's runtime detection of the sandbox-escape staging step.
       strength: secondary
-
 tags:
   category: privilege-escalation
   subcategory: git-worktree-directory-confusion
   scan_target: llm_io
   confidence: medium
-
 agent_source:
   type: llm_io
   framework:
     - any
   provider:
     - any
-
 detection:
   condition: any
   conditions:
     - field: content
       operator: regex
-      value: '(?i)\bgit\s+worktree\s+add\b[\s\S]{0,40}?(?:^|[\\/\s])\.git(?:\s|$|["''\x60])'
-      description: "git worktree add invocation whose worktree path component is the reserved name .git, not an ordinary worktree/branch name"
+      value: (?i)\bgit\s+worktree\s+add\b[\s\S]{0,40}?(?:^|[\\/\s])\.git(?:\s|$|["'\x60])
+      description: git worktree add invocation whose worktree path component is the reserved name .git, not an ordinary worktree/branch name
   false_positives:
-    - "A 'git worktree add' command followed elsewhere in the same line by an unrelated file named with a .git-prefixed extension, such as .gitignore or .gitattributes -- excluded because the pattern requires .git to be immediately followed by whitespace, end of string, or a quote, not additional letters"
-    - "A bare-repository path that happens to end in .git as a suffix of a longer name, e.g. 'git worktree add /srv/repos/myproject.git feature-branch' -- excluded because the pattern requires .git to be preceded by a path separator or whitespace, not by another word character"
-    - "Documentation or an advisory discussing the .git worktree-naming technique in prose without an actual 'git worktree add' command being issued"
-
+    - A 'git worktree add' command followed elsewhere in the same line by an unrelated file named with a .git-prefixed extension, such as .gitignore or .gitattributes -- excluded because the pattern requires .git to be immediately followed by whitespace, end of string, or a quote, not additional letters
+    - A bare-repository path that happens to end in .git as a suffix of a longer name, e.g. 'git worktree add /srv/repos/myproject.git feature-branch' -- excluded because the pattern requires .git to be preceded by a path separator or whitespace, not by another word character
+    - Documentation or an advisory discussing the .git worktree-naming technique in prose without an actual 'git worktree add' command being issued
 response:
   actions:
     - block_input
     - alert
-  message_template: >
-    [ATR-2026-02302] A git worktree is being created with the reserved name
-    .git -- treat as a directory-confusion sandbox-escape staging step, not
-    a routine worktree operation.
-
+  message_template: |
+    [ATR-2026-02302] A git worktree is being created with the reserved name .git -- treat as a directory-confusion sandbox-escape staging step, not a routine worktree operation.
 confidence: 68
-
-test_cases:
-  true_positives:
-    - input: "git worktree add ../.git some-branch && cd ../.git"
-      expected: triggered
-      description: "CVE-2026-55607 pattern - worktree created with the reserved name .git"
-    - input: "run: git worktree add .git feature/exploit"
-      expected: triggered
-      description: "Worktree path is literally .git in the current directory"
-    - input: "git worktree add \"../.git\" main"
-      expected: triggered
-      description: "Quoted worktree path .git, still matches the reserved-name signature"
-  true_negatives:
-    - input: "git worktree add ../feature-branch feature/new-thing"
-      expected: not_triggered
-      description: "Ordinary worktree with a normal descriptive name, not .git"
-    - input: "git worktree add /srv/repos/myproject.git feature-branch"
-      expected: not_triggered
-      description: "Bare-repository convention path ending in .git as a suffix, not a standalone .git path component"
-    - input: "git worktree add new-feature branch-x  # see .gitignore for excluded paths"
-      expected: not_triggered
-      description: ".gitignore mentioned elsewhere on the line, not the worktree path itself"
-    - input: "The advisory explains that creating a worktree named .git can trigger directory confusion."
-      expected: not_triggered
-      description: "Documentation/advisory prose describing the technique, no actual git worktree add command issued"

package/rules/privilege-escalation/ATR-2026-02353-runtime-identifier-field-path-traversal-log-read.yaml

@@ -1,168 +1,87 @@
-title: "Agent-Runtime Identifier Field (run_id/agent_id/session_id/task_id) Carries Path Traversal Into a History/Log File Read"
+title: Agent-Runtime Identifier Field (run_id/agent_id/session_id/task_id) Carries Path Traversal Into a History/Log File Read
 id: ATR-2026-02353
 rule_version: 1
 status: experimental
-description: >
-  Detects an agent-runtime identifier argument (run_id, agent_id,
-  session_id, execution_id, task_id) that contains a path-traversal
-  sequence or an absolute path targeting a sensitive system directory, when
-  that identifier is used as a filesystem-path component for reading
-  history/terminal/log artifacts. Ordinary runtime identifiers are opaque
-  tokens (UUIDs, short alphanumeric run IDs) and legitimately never contain
-  "../" or start with "/etc", "/root", etc. -- the presence of traversal or
-  an absolute system path inside a field whose name signals it should be a
-  bare identifier is itself the attack. Mined from GHSA-22cj-m4wf-fv2c
-  (PraisonAI's Dynamic Context module exposes agent-callable
-  `history_search`/`history_tail`/`history_get` and
-  `terminal_tail`/`terminal_grep`/`terminal_commands` tools that join a
-  caller-supplied `run_id` and `agent_id` directly into a filesystem path --
-  `self.base_dir / run_id / "history" / f"{agent_id}.jsonl"` -- with no
-  rejection of an absolute `run_id` or a traversal-bearing `agent_id`,
-  letting a lower-trust prompt/user read .jsonl/.log files outside the
-  configured Dynamic Context base directory). This is a distinct field
-  -name family (runtime/session-scoped: run_id/agent_id/session_id/
-  execution_id/task_id) and a different source product from
-  ATR-2026-02251 (tenant/owner-scoped: sender_id/owner_id/tenant_id/
-  user_id/project_id/app_id/workspace_id, mined from EverOS/CVE-2026-58499)
-  -- the two rules are complementary members of the same broader
-  "opaque-identifier-field carrying path traversal" class rather than
-  duplicates of one another.
-author: "ATR Community (CVE sweep)"
-date: "2026/07/11"
-schema_version: "0.1"
+description: |
+  Detects an agent-runtime identifier argument (run_id, agent_id, session_id, execution_id, task_id) that contains a path-traversal sequence or an absolute path targeting a sensitive system directory, when that identifier is used as a filesystem-path component for reading history/terminal/log artifacts. Ordinary runtime identifiers are opaque tokens (UUIDs, short alphanumeric run IDs) and legitimately never contain "../" or start with "/etc", "/root", etc. -- the presence of traversal or an absolute system path inside a field whose name signals it should be a bare identifier is itself the attack. Mined from GHSA-22cj-m4wf-fv2c (PraisonAI's Dynamic Context module exposes agent-callable `history_search`/`history_tail`/`history_get` and `terminal_tail`/`terminal_grep`/`terminal_commands` tools that join a caller-supplied `run_id` and `agent_id` directly into a filesystem path -- `self.base_dir / run_id / "history" / f"{agent_id}.jsonl"` -- with no rejection of an absolute `run_id` or a traversal-bearing `agent_id`, letting a lower-trust prompt/user read .jsonl/.log files outside the configured Dynamic Context base directory). This is a distinct field -name family (runtime/session-scoped: run_id/agent_id/session_id/ execution_id/task_id) and a different source product from ATR-2026-02251 (tenant/owner-scoped: sender_id/owner_id/tenant_id/ user_id/project_id/app_id/workspace_id, mined from EverOS/CVE-2026-58499) -- the two rules are complementary members of the same broader "opaque-identifier-field carrying path traversal" class rather than duplicates of one another.
+author: ATR Community (CVE sweep)
+date: 2026/07/11
+schema_version: '0.1'
 detection_tier: pattern
 maturity: experimental
 severity: high
-
 references:
   cwe:
-    - "CWE-200"
-    - "CWE-22"
+    - CWE-200
+    - CWE-22
   owasp_llm:
-    - "LLM02:2025"
+    - LLM02:2025
   owasp_agentic:
-    - "ASI02:2026"
+    - ASI02:2026
   mitre_attack:
-    - "T1083 - File and Directory Discovery"
+    - T1083 - File and Directory Discovery
   mitre_atlas:
-    - "AML.T0057 - LLM Data Leakage"
+    - AML.T0057 - LLM Data Leakage
   external:
-    - "https://github.com/advisories/GHSA-22cj-m4wf-fv2c"
-
+    - https://github.com/advisories/GHSA-22cj-m4wf-fv2c
 metadata_provenance:
   cwe: human-reviewed
   owasp_llm: human-reviewed
   owasp_agentic: human-reviewed
   mitre_attack: human-reviewed
   mitre_atlas: human-reviewed
-
 compliance:
   eu_ai_act:
-    - article: "15"
-      context: "Article 15 (accuracy, robustness and cybersecurity) requires resistance to unauthorised data access; this rule detects a runtime identifier field being weaponised for path traversal into a history/log file read, breaking the configured storage boundary."
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) requires resistance to unauthorised data access; this rule detects a runtime identifier field being weaponised for path traversal into a history/log file read, breaking the configured storage boundary.
       strength: primary
-    - article: "9"
-      context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for the runtime-identifier-path-traversal risk class."
+    - article: '9'
+      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for the runtime-identifier-path-traversal risk class.
       strength: secondary
   nist_ai_rmf:
-    - subcategory: "MG.2.3"
-      context: "Treating runtime-identifier-field path traversal as an identified AI risk requires active runtime countermeasures; this detection rule is the primary risk treatment implementation."
+    - subcategory: MG.2.3
+      context: Treating runtime-identifier-field path traversal as an identified AI risk requires active runtime countermeasures; this detection rule is the primary risk treatment implementation.
       strength: primary
-    - subcategory: "MP.5.1"
-      context: "Identifying the runtime-identifier-path-traversal pattern as an AI risk to be catalogued in the organizational risk register."
+    - subcategory: MP.5.1
+      context: Identifying the runtime-identifier-path-traversal pattern as an AI risk to be catalogued in the organizational risk register.
       strength: secondary
   iso_42001:
-    - clause: "8.1"
-      context: "ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by this rule's detection of runtime-identifier path traversal attempts."
+    - clause: '8.1'
+      context: ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by this rule's detection of runtime-identifier path traversal attempts.
       strength: primary
-    - clause: "8.3"
-      context: "ISO/IEC 42001 Clause 8.3 (AI risk treatment) is implemented via this rule's runtime detection of the traversal attempt."
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is implemented via this rule's runtime detection of the traversal attempt.
       strength: secondary
-
 tags:
   category: privilege-escalation
   subcategory: runtime-identifier-path-traversal
   scan_target: llm_io
   confidence: high
-
 agent_source:
   type: llm_io
   framework:
     - any
   provider:
     - any
-
 detection:
   condition: any
   conditions:
     - field: content
       operator: regex
-      value: '\b(run_id|agent_id|session_id|execution_id|task_id)\b\s*(?:[=:]|(?:is\s+)?set\s+to)\s*["\x27]?(?:\.\.(?:/|%2f)|%2e%2e(?:/|%2f))'
-      description: "Runtime identifier field carrying a literal or percent-encoded relative path-traversal sequence -- the connector is restricted to an actual assignment token (:, =, \"set to\", \"is set to\"), so ordinary security-guidance prose like 'run_id never contains ../' does not match, and a bare standalone 'to' is no longer accepted as a connector either (see false_positives; an earlier version accepted bare 'to' and matched ordinary prepositional phrasing like 'point your run_id to ../shared/logs', which is not an assignment)"
+      value: \b(run_id|agent_id|session_id|execution_id|task_id)\b\s*(?:[=:]|(?:is\s+)?set\s+to)\s*["\x27]?(?:\.\.(?:/|%2f)|%2e%2e(?:/|%2f))
+      description: Runtime identifier field carrying a literal or percent-encoded relative path-traversal sequence -- the connector is restricted to an actual assignment token (:, =, "set to", "is set to"), so ordinary security-guidance prose like 'run_id never contains ../' does not match, and a bare standalone 'to' is no longer accepted as a connector either (see false_positives; an earlier version accepted bare 'to' and matched ordinary prepositional phrasing like 'point your run_id to ../shared/logs', which is not an assignment)
     - field: content
       operator: regex
-      value: '\b(run_id|agent_id|session_id|execution_id|task_id)\b\s*(?:[=:]|(?:is\s+)?set\s+to)\s*["\x27]?/(?:etc|root|proc|home|var/(?:log|lib))\b'
-      description: "Runtime identifier field set to an absolute path targeting a sensitive system directory -- exploits the identifier being used unvalidated as a base-path component rather than an opaque token. Same assignment-token restriction as the traversal condition (bare 'to' is not accepted as a connector)."
+      value: \b(run_id|agent_id|session_id|execution_id|task_id)\b\s*(?:[=:]|(?:is\s+)?set\s+to)\s*["\x27]?/(?:etc|root|proc|home|var/(?:log|lib))\b
+      description: Runtime identifier field set to an absolute path targeting a sensitive system directory -- exploits the identifier being used unvalidated as a base-path component rather than an opaque token. Same assignment-token restriction as the traversal condition (bare 'to' is not accepted as a connector).
   false_positives:
-    - "A legitimate identifier value that happens to be discussed in prose alongside the word 'traversal' or a path-like example without the field actually being assigned a traversal sequence or absolute system path (e.g. 'validate that run_id never contains ../ before using it' -- no assignment connector directly precedes the traversal marker, so this does not match)"
-    - "Documentation showing the vulnerable field/sink relationship as example code, not an actual argument being set"
-    - "Ordinary bug-report/chat-style prose using 'to' as a preposition rather than an assignment, e.g. 'point your run_id to ../shared/logs' or 'I changed session_id to /etc/hosts by mistake' -- a bare standalone 'to' is not accepted as a connector, only actual assignment tokens (:, =, 'set to', 'is set to')"
-
+    - A legitimate identifier value that happens to be discussed in prose alongside the word 'traversal' or a path-like example without the field actually being assigned a traversal sequence or absolute system path (e.g. 'validate that run_id never contains ../ before using it' -- no assignment connector directly precedes the traversal marker, so this does not match)
+    - Documentation showing the vulnerable field/sink relationship as example code, not an actual argument being set
+    - Ordinary bug-report/chat-style prose using 'to' as a preposition rather than an assignment, e.g. 'point your run_id to ../shared/logs' or 'I changed session_id to /etc/hosts by mistake' -- a bare standalone 'to' is not accepted as a connector, only actual assignment tokens (:, =, 'set to', 'is set to')
 response:
   actions:
     - block_input
     - alert
-  message_template: >
-    [ATR-2026-02353] Agent-runtime identifier field (run_id/agent_id/
-    session_id/execution_id/task_id) carries a path-traversal sequence or
-    targets a sensitive system directory -- treat as an attempt to read a
-    history/log file outside the configured storage boundary, not a normal
-    identifier.
-
+  message_template: |
+    [ATR-2026-02353] Agent-runtime identifier field (run_id/agent_id/ session_id/execution_id/task_id) carries a path-traversal sequence or targets a sensitive system directory -- treat as an attempt to read a history/log file outside the configured storage boundary, not a normal identifier.
 confidence: 78
-
-test_cases:
-  true_positives:
-    - input: 'call history_search with run_id: "../../../../home/user/.aws/credentials"'
-      expected: triggered
-      description: "GHSA-22cj-m4wf-fv2c pattern -- run_id path traversal targeting AWS credentials"
-    - input: 'terminal_tail(agent_id="../../../../root/.ssh/authorized_keys")'
-      expected: triggered
-      description: "agent_id traversal targeting an SSH authorized_keys file"
-    - input: 'call history_get with run_id set to "/etc/passwd"'
-      expected: triggered
-      description: "run_id set to an absolute system path rather than an opaque token"
-    - input: 'terminal_grep(session_id="../../../../var/log/auth.log")'
-      expected: triggered
-      description: "Different identifier field name (session_id) targeting a sensitive log file"
-    - input: 'call terminal_commands with task_id: "../../../../proc/self/environ"'
-      expected: triggered
-      description: "Different identifier field name (task_id) targeting environment-variable disclosure"
-  true_negatives:
-    - input: 'call history_search with run_id: "run-8f3ab2c1-4d9e-4a7b-9c3d-1e2f3a4b5c6d"'
-      expected: not_triggered
-      description: "Ordinary opaque UUID-style run_id, no traversal characters"
-    - input: 'terminal_tail(agent_id="agent-042")'
-      expected: not_triggered
-      description: "Ordinary short alphanumeric agent_id, no traversal"
-    - input: "PraisonAI's history_search/terminal_tail tools join run_id and agent_id into a filesystem path without validating for traversal, per GHSA-22cj-m4wf-fv2c."
-      expected: not_triggered
-      description: "Advisory prose describing the vulnerability class, no field actually set to a traversal or absolute-path value"
-    - input: "Best practice: validate that run_id never contains ../ before using it in a path."
-      expected: not_triggered
-      description: "ADVERSARIAL SELF-REVIEW FINDING (fixed): security-guidance prose using the field name and the traversal string in the same sentence, but with no assignment. An earlier draft of this condition used a generic bounded-character-gap connector ([^\\n\"']{0,20}) that matched 'run_id never contains ../' as if it were an assignment; the connector is now restricted to actual assignment tokens (:, =, 'set to', 'is set to') immediately preceding the traversal marker, so this prose no longer matches."
-    - input: "Fixed: agent_id is now checked so it can never contain ../ segments before being joined into a path."
-      expected: not_triggered
-      description: "Changelog/fix-description prose, same shape as the finding above -- no assignment connector directly before the traversal marker"
-    - input: "Please point your run_id to ../shared/logs for the shared test run."
-      expected: not_triggered
-      description: "ADVERSARIAL SELF-REVIEW FINDING ROUND 2 (fixed): bare 'to' used as an ordinary preposition ('point X to Y'), not an assignment. The prior fix only restricted the connector's bounded-gap character class but still accepted a standalone 'to' as a connector option, so this ordinary bug-report/chat phrasing still matched. 'to' is no longer accepted alone -- only ':', '=', 'set to', 'is set to'."
-    - input: "I changed session_id to /etc/hosts by mistake in the config, please fix it."
-      expected: not_triggered
-      description: "ADVERSARIAL SELF-REVIEW FINDING ROUND 2 (fixed): same bare-'to'-as-preposition class as above, hitting the absolute-system-path condition instead of the traversal-sequence condition."
-
-evasion_tests:
-  - input: 'call history_search with run_id: "....//....//....//home/user/.aws/credentials"'
-    expected: not_triggered
-    bypass_technique: doubled_dot_dot_slash_obfuscation
-    notes: "A doubled '....//' sequence that some naive path sanitizers strip down to '../' after one pass is not caught by this rule's literal '../' match. Documented as a known gap; a follow-up rule iteration should add a normalization-aware or repetition-tolerant variant if this bypass is confirmed exploitable against the target sanitizer."