cw-final-pass

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided drafts which could contain instructions intended to influence the AI's behavior.
  • Ingestion points: User-provided drafts and the local context file at ../../references/context-contract.md.
  • Boundary markers: The instructions do not define clear delimiters or warnings to isolate the draft content from the skill's operational logic.
  • Capability inventory: The skill is restricted to text generation and assessment; it does not utilize file-writing, network requests, or shell execution tools.
  • Sanitization: No explicit sanitization or input validation is performed on the ingested draft content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:43 PM
Security Audit — agent-trust-hub — cw-final-pass