spec-it
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository and user conversations to generate specifications.
- Ingestion points: Reads repository instructions, existing code context, tests, and conversation history.
- Boundary markers: The skill does not define specific delimiters for separating repository content from instructions.
- Capability inventory: The skill performs file system writes to save the generated specifications based on the synthesized data.
- Sanitization: No explicit sanitization or instruction-ignoring logic is defined for the ingested data.
Audit Metadata