judge

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external files which could contain malicious instructions designed to influence the agent's behavior during the review process.
  • Ingestion points: The skill reads draft-N.md, draft-N-human-edits.md, and potentially output from the-fool skill as described in the Core Workflow (Step 1) and Handling Fool Output sections of SKILL.md.
  • Boundary markers: The instructions do not specify the use of clear delimiters or instructions to the model to ignore embedded commands within the draft text being audited.
  • Capability inventory: The skill possesses the capability to read from and write to the local file system (producing final-draft-X.md files) and interact with the user through AskUserQuestion.
  • Sanitization: There is no evidence of explicit sanitization, filtering, or validation of the text content ingested from the draft files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 12:42 AM
Security Audit — agent-trust-hub — judge