test-spec

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted documentation files to generate output, which creates a surface for indirect prompt injection.\n
  • Ingestion points: Reads from docs/PRD.md, docs/IMPLEMENTATION_GUIDE.md, docs/UX_SPEC.md, and docs/ARCHITECTURE.md.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for content interpolated from these files.\n
  • Capability inventory: The agent has Read and Write access to the local filesystem and can interact with the user via AskUserQuestion.\n
  • Sanitization: There is no mention of sanitizing or validating the content ingested from source documents before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 01:19 PM
Security Audit — agent-trust-hub — test-spec