skill-installer
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches skill data and archives from GitHub, including the official OpenAI skills repository. This behavior is the intended core functionality of the skill installer.
- [COMMAND_EXECUTION]: Executes
gitcommands usingsubprocess.runto handle repository checkouts. The implementation uses argument lists rather than shell strings, which is a secure practice. - [SAFE]: Implements protective measures such as
_safe_extract_zipto prevent path traversal attacks when extracting downloaded skill archives. It also correctly accessesGITHUB_TOKENfrom the environment for API authentication, which is standard practice.
Audit Metadata