bug-triage
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'Bash' tool to execute GitHub CLI ('gh') commands for fetching, commenting on, and closing issues. While standard for this workflow, shell execution based on external data requires careful handling by the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issue comments which could contain instructions intended to influence the agent's behavior.
- Ingestion points: GitHub issue content and comments are fetched in 'SKILL.md' using 'gh issue view --comments'.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the fetched issue content.
- Capability inventory: The skill possesses the ability to execute shell commands via 'Bash' (GitHub CLI) and perform web requests via 'WebFetch'.
- Sanitization: The risk is significantly mitigated by a mandatory human-in-the-loop requirement defined in 'Step 4', where the user must explicitly approve any proposed actions and response drafts before the agent proceeds to 'Step 5'.
Audit Metadata