to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user conversations and repository content to generate planning specs and issues, which could potentially incorporate malicious instructions from the input data.
- Ingestion points: Current conversation history and repository files (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded within the conversation data.
- Capability inventory: The skill is capable of exploring the repository and publishing work items to external trackers (SKILL.md).
- Sanitization: There is no evidence of sanitization or filtering of the input conversation before it is synthesized into artifacts.
Audit Metadata