to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its ingestion of external project data.
- Ingestion points: User-supplied plans, specs, and PRDs, as well as content fetched from issue tracker bodies and comments (SKILL.md).
- Boundary markers: No explicit delimiter or 'ignore instructions' markers are defined for the input data.
- Capability inventory: The skill has the capability to read from and write to an external issue tracker.
- Sanitization: No evidence of sanitization or validation of the ingested content was found.
- Mitigation: The skill implements a mandatory 'Quiz the user' step which acts as a manual review phase before any issues are published to the tracker, significantly mitigating the risk of malicious instructions being executed.
Audit Metadata