to-spec
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to synthesize a technical specification from the current conversation and codebase.
- [DATA_EXFILTRATION]: The skill instructs the agent to publish the generated spec to a project issue tracker. This is the primary function of the skill and utilizes intended tool capabilities for project management.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from repository files (ADRs and glossaries) and the conversation history.
- Ingestion points: Repository files and conversation history
- Boundary markers: None identified
- Capability inventory: File read and issue tracker write
- Sanitization: None identified
Audit Metadata