to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the conversation history and repository content to synthesize a technical specification and publish it to an issue tracker. This surface could be used to influence the generated spec or metadata if malicious instructions are embedded in the conversation or code comments.
- Ingestion points: Conversation context and codebase understanding as specified in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or 'ignore' instructions for processing the ingested context.
- Capability inventory: Includes repository exploration (read access) and publishing to an issue tracker (write access).
- Sanitization: No sanitization or validation of the input data is performed before synthesis.
Audit Metadata