to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from an external issue tracker, creating an indirect prompt injection surface.
- Ingestion points: Step 1 in
SKILL.mdinstructs the agent to fetch and read the full body and comments of issues from the issue tracker. - Boundary markers: No specific boundary markers or instructions to ignore nested commands are provided for the fetched data.
- Capability inventory: The agent has the capability to explore the local codebase and publish new issues to the tracker.
- Sanitization: The instructions do not specify any sanitization or validation of the fetched issue content.
- Mitigation: Step 4 requires the agent to 'Quiz the user' and iterate until the user approves the breakdown, providing a human checkpoint before publication.
Audit Metadata