to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, such as data exfiltration, obfuscation, or unauthorized command execution, were detected in the skill instructions. The logic follows established software development practices for breaking down requirements.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external issue tracker bodies and comments. However, the design includes robust mitigations that justify a safe assessment.
- Ingestion points: Step 1 in
SKILL.md(fetches full body and comments of issues from the issue tracker). - Boundary markers: Absent.
- Capability inventory: Codebase exploration and publishing new issues to an issue tracker.
- Sanitization: Absent.
- Mitigation: The skill strictly adheres to a human-in-the-loop (HITL) process (Step 4), where the proposed breakdown must be reviewed and approved by the user before any issues are published. This ensures that any malicious instructions embedded in the source data would be visible to the user during the drafting phase and could not be automatically executed.
Audit Metadata