to-issues
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions do not contain malicious patterns, obfuscation, or unauthorized data exfiltration logic.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by design, as it ingests data from external issue trackers.
- Ingestion points: Reads full bodies and comments from issue trackers in
SKILL.md. - Boundary markers: No explicit delimiters or instruction-ignore blocks are defined for external content.
- Capability inventory: codebase exploration (read) and issue publishing (write).
- Sanitization: No sanitization logic is provided in the instructions.
- Mitigation: The risk is effectively mitigated by a mandatory human-in-the-loop verification step where the agent must present the proposed breakdown for user approval before publishing.
Audit Metadata