to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected in the skill instructions. The skill operates within a restricted scope of document synthesis and project management.- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history to generate documentation, presenting a surface for indirect prompt injection. This is mitigated by requiring explicit user review and confirmation of the generated draft. 1. Ingestion points: conversation history (runtime context). 2. Boundary markers: None. 3. Capability inventory: File system write access to docs/specs/ (SKILL.md). 4. Sanitization: None.
Audit Metadata