find-skills
Warn
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
npx skillsCLI tool. This includes searching for packages and adding them to the system based on user-provided input, which could lead to command injection if input is not properly handled. - [EXTERNAL_DOWNLOADS]: The skill facilitates downloading software packages from external repositories, specifically from
skills.shand various GitHub repositories. This introduces risks associated with third-party code and supply chain security, as these sources are not restricted to trusted registries. - [REMOTE_CODE_EXECUTION]: The
npx skills addcommand is used to install and potentially execute remote code. The skill explicitly recommends using the-yflag to skip user confirmation prompts and the-gflag for global installation, which reduces user oversight and increases the potential impact of a malicious package.
Audit Metadata