to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the codebase and conversation history to synthesize a specification. This creates a surface where malicious instructions embedded in project files could attempt to influence the agent's behavior during the synthesis process.
- Ingestion points: Current conversation context and codebase files (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands within the source data.
- Capability inventory: The skill writes to the local filesystem (under
.efforts/) and interacts with an external or local issue tracker (SKILL.md). - Sanitization: No explicit sanitization or validation of the synthesized content is mentioned before publication.
- [SAFE]: The skill follows standard documentation practices and includes instructions for the agent to check with the user regarding testing seams, ensuring a human-in-the-loop for architectural decisions.
Audit Metadata