to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the current conversation and repository files to generate specifications that are then published to an external issue tracker.
- Ingestion points: The skill explicitly reads from the "current conversation context" and "codebase understanding" (SKILL.md).
- Boundary markers: Absent. No specific delimiters or instructions are provided to the agent to disregard malicious directives embedded in the codebase or user chat.
- Capability inventory: The agent has the ability to explore the repository and publish content to the project issue tracker (SKILL.md).
- Sanitization: Absent. The skill does not define validation or escaping steps for the ingested data before it is formatted into the final spec template.
Audit Metadata