gh-cli
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified.
- [COMMAND_EXECUTION]: Recommends using the official
ghCLI for tasks like viewing repositories, pull requests, and issues. - [EXTERNAL_DOWNLOADS]: Suggests cloning repositories and using the GitHub API via the CLI, which are standard operations for a well-known and trusted service.
- [PROMPT_INJECTION]: The skill interacts with external data (GitHub PRs and issues) that could contain malicious instructions. This represents a surface for indirect prompt injection, but it is necessary for the skill's primary function and no exploitation was found. Evidence: 1. Ingestion points:
gh pr view,gh issue view(SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory:ghcommand execution (SKILL.md). 4. Sanitization: Absent.
Audit Metadata