doc-bdd-reviewer

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the sha256sum utility in a bash environment to perform integrity checks and detect content drift in project documents. This is a standard utility for the skill's documented workflow.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted data from external documentation files and uses that data in shell commands.
  • Ingestion points: The skill extracts information from @ref: and @ears: tags within BDD feature files and Markdown documents located in the docs/ directory.
  • Boundary markers: Absent; there are no specified delimiters or instructions for the agent to ignore embedded instructions within the ingested document content.
  • Capability inventory: The skill utilizes shell command execution (bash / sha256sum) and performs local file system write operations (creating reports and updating .drift_cache.json).
  • Sanitization: Absent; the skill does not define validation, escaping, or filtering procedures for the file paths extracted from untrusted document content before they are used as command arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 11:59 AM
Security Audit — agent-trust-hub — doc-bdd-reviewer