skill-installer

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches skill listings and file content from GitHub.
  • Evidence: The skill connects to api.github.com and codeload.github.com in scripts/list-curated-skills.py and scripts/install-skill-from-github.py.
  • Context: The default source is openai/skills, which is a trusted organization.
  • [COMMAND_EXECUTION]: Uses the git command-line tool via subprocess to download repository content.
  • Evidence: Employs subprocess.run for git clone and sparse-checkout operations in scripts/install-skill-from-github.py.
  • [DATA_EXFILTRATION]: Handles GitHub tokens for authenticated requests.
  • Evidence: The github_utils.py script reads GITHUB_TOKEN from environment variables and provides it to GitHub API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:22 PM