create-agent-skills
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to manage files within the
~/.claude/directory, including listing, reading, and creating skill structures. This is core functionality for its purpose of skill management. - [COMMAND_EXECUTION]: Employs the
chmod +xcommand to make supporting scripts executable, which is a standard procedure for skill development. - [EXTERNAL_DOWNLOADS]: Contains instructions and examples for installing Python packages using
pip, though it does not automatically execute installations from untrusted sources. - [CREDENTIALS_UNSAFE]: Interacts with
~/.claude/.envfor managing API credentials. Critically, it includes a comprehensive security guide (references/api-security.md) that instructs users on how to avoid exposing these credentials in chat logs by using wrapper scripts and environment variables.
Audit Metadata