to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and YAML configuration. It does not ship any executable scripts, binaries, or automated installation procedures.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from the conversation history and the codebase to generate specifications.
- Ingestion points: Reads from current conversation context and codebase (SKILL.md).
- Boundary markers: None present to distinguish between instructions and data.
- Capability inventory: The skill publishes content to an issue tracker.
- Sanitization: No explicit sanitization of input data is defined.
- Note: While the ingestion of untrusted data presents an attack surface, the risk is minimized as the output is restricted to document generation in an issue tracker.
Audit Metadata