to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides clear instructions for a project management workflow and does not contain any malicious code, obfuscated commands, or unauthorized network operations.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external, untrusted data from an issue tracker.
- Ingestion points: Step 1 describes fetching issue data from an issue tracker and reading conversation context.
- Boundary markers: No explicit boundary markers or isolation instructions are provided for the ingested data.
- Capability inventory: The skill allows the agent to explore the local codebase (Step 2) and perform write operations to the issue tracker (Step 5).
- Sanitization: While no automated sanitization is defined, the workflow includes a mandatory human-in-the-loop step (Step 4) that requires user approval before issues are published, which effectively mitigates automated injection risks.
Audit Metadata