to-issues

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external project documentation and issue tracker content.
  • Ingestion points: Reads issue bodies, comments, and project specifications (SKILL.md).
  • Boundary markers: Lacks explicit separators for untrusted data.
  • Capability inventory: Authorized to read codebase files and create issues in the project tracker.
  • Sanitization: Does not explicitly sanitize external text.
  • Mitigation: The workflow includes a mandatory user approval step ('Quiz the user') before any issues are published, which effectively mitigates the risk of the agent acting on malicious instructions hidden in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:12 AM
Security Audit — agent-trust-hub — to-issues