review-document

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external document content.
  • Ingestion points: Document content is ingested from the docs/ directory or user-provided paths in Step 1.
  • Boundary markers: The skill does not define specific delimiters or include instructions for the agent to ignore embedded commands within the text being reviewed.
  • Capability inventory: The agent is authorized to read filesystem content and perform inline file updates (writes) in Step 5.
  • Sanitization: No validation or sanitization of the input text is required by the instructions.
  • [NO_CODE]: The skill consists exclusively of markdown-based natural language instructions and does not include any scripts, binaries, or external code dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:42 PM