using-gh-cli-search

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill provides guidelines for the agent to follow when assisting users with GitHub CLI commands. The focus is on preventing syntax errors (like missing the -- flag) rather than performing any dangerous operations.
  • [PROMPT_INJECTION]: The skill uses strong, imperative language (e.g., "MANDATORY", "not optional", "not negotiable") to ensure the agent uses specialized sub-skills for GitHub CLI searches. These instructions are functional constraints designed to improve technical accuracy and do not attempt to bypass core safety or ethical guardrails.
  • [EXTERNAL_DOWNLOADS]: References to other skills such as gh-search-code and gh-cli-setup are pointers to internal platform capabilities rather than requests to download and execute code from untrusted external sources.
  • [COMMAND_EXECUTION]: The skill includes examples of shell commands (e.g., gh search issues -- "is:open -label:bug"), but these are provided as pedagogical examples of correct syntax for the user to copy, not as commands the agent should execute silently or maliciously.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 11:43 AM