anthropic-claude-code
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill package is composed entirely of Markdown documentation files intended as a reference for the Claude Code CLI tool.
- [SAFE]: No active code, scripts, or automated tools are included that would execute in the agent's environment.
- [EXTERNAL_DOWNLOADS]: The documentation includes instructions for installing the CLI via a shell script from a trusted vendor domain (claude.ai). This is consistent with the skill's purpose as a setup guide and targets a known, reputable service.
- [SAFE]: Mention of powerful capabilities like the dynamic context injection (exclamation mark backtick syntax) and the --dangerously-skip-permissions flag are provided solely in the context of official documentation and troubleshooting, rather than as an attempt to exploit the agent or user environment.
Audit Metadata