work-issues
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs repository operations using standard CLI tools including git and gh (GitHub CLI) to manage branches, commit code, and create pull requests. These capabilities are consistent with the skill's primary function of automating developer workflows.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from GitHub issue titles and bodies. 1. Ingestion points: Untrusted data enters via gh issue list and gh issue body retrieval in SKILL.md. 2. Boundary markers: No delimiters or explicit instructions to ignore embedded commands within issue content are provided. 3. Capability inventory: The agent is authorized to perform git push, gh pr create, and modify issue labels/comments. 4. Sanitization: No sanitization or validation of the ingested issue content is performed before the agent processes it.
Audit Metadata