doc-review

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) as it processes untrusted documentation files.\n
  • Ingestion points: Documentation files identified by the user and read during the review process.\n
  • Boundary markers: The instructions provided to sub-agents do not include delimiters (like XML tags) or specific directives to ignore instructions found within the source documents.\n
  • Capability inventory: The skill possesses filesystem read capabilities and can invoke sub-agents via the Task tool.\n
  • Sanitization: No validation or sanitization of the input file content is performed before processing.\n- [COMMAND_EXECUTION]: The skill uses Python's glob and os modules to perform file discovery and path resolution based on user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 04:25 AM