gh
Warn
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill instructs users to install an extension from an untrusted GitHub repository (
yahsan2/gh-sub-issue). Evidence:gh extension install yahsan2/gh-sub-issue. - PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it reads and displays content from GitHub which can be controlled by external attackers. 1. Ingestion points:
gh issue view,gh issue list,gh pr checks,gh run view --log. 2. Boundary markers: Absent. 3. Capability inventory: Bash command execution and GitHub API modifications (merge, comment, create). 4. Sanitization: Absent. - COMMAND_EXECUTION (SAFE): The skill uses the Bash tool to execute standard GitHub CLI commands, which is consistent with its stated purpose of providing a CLI reference.
Audit Metadata