to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository and conversation history to generate project specifications.
- Ingestion points: The agent is instructed to "Explore the repo" and use "current conversation context" (SKILL.md) to synthesize requirements and technical decisions.
- Boundary markers: The instructions lack explicit delimiters or safety warnings to ensure the agent ignores instructions potentially embedded within repository files or conversation logs during the synthesis process.
- Capability inventory: The skill enables the agent to read repository content and publish the resulting synthesis to an external issue tracker.
- Sanitization: No content filtering, validation, or escaping mechanisms are defined for the repository data or conversation history before processing.
Audit Metadata