document-review

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill lacks safeguards against indirect prompt injection when processing untrusted document content.
  • Ingestion points: Step 1 reads data from files provided by the user or found in the docs/ directory.
  • Boundary markers: The skill does not implement delimiters or specific instructions to ignore embedded commands within the processed text.
  • Capability inventory: The agent is empowered to read and update files based on the document content.
  • Sanitization: No validation or sanitization of document content is performed before it is added to the model's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 05:36 PM