interrogate-plan

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted content from the codebase to inform its actions. \n
  • Ingestion points: The agent reads CONTEXT.md, CONTEXT-MAP.md, architecture records in docs/adr/, and source files in src/. \n
  • Boundary markers: No delimiters or specific instructions are provided to help the agent ignore embedded commands within the analyzed files. \n
  • Capability inventory: The agent has permissions to read various project files and write updates to documentation files like CONTEXT.md and ADRs. \n
  • Sanitization: No validation or escaping of the input data is performed before it is used to generate or modify project documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:08 PM
Security Audit — agent-trust-hub — interrogate-plan