to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation context and codebase content to generate specifications, presenting a typical surface for indirect prompt injection.
- Ingestion points: Conversation history and repository exploration (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded directives are provided.
- Capability inventory: Accesses repository files and publishes content to a project issue tracker (SKILL.md).
- Sanitization: No explicit sanitization or data validation methods are mentioned.
Audit Metadata