to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository and conversation context to generate and publish specifications.
- Ingestion points: The skill reads the current conversation context and performs repository exploration to understand the codebase state, which could contain malicious instructions (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore embedded instructions found within the repository or conversation history.
- Capability inventory: The skill utilizes tools to explore the filesystem/repository and publish content to an external issue tracker.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested codebase content before it is incorporated into the published spec.
Audit Metadata