to-issues
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process untrusted data from external URLs, issue trackers, and project files.
- Ingestion points: Step 1 (Gather context) describes fetching content from issue references, URLs, or file paths provided by the user.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the fetched external data.
- Capability inventory: The skill has the capability to read codebase files (Step 2) and publish new issues to a project tracker (Step 5).
- Sanitization: There are no explicit sanitization or validation steps for the content fetched from external sources.
- Mitigation: The risk is significantly reduced by Step 4 (Quiz the user), which requires the agent to present the proposed issues to a human for approval before performing any write operations to the issue tracker.
Audit Metadata