claude-code-best-practices
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell commands like
catandgrepto search through local documentation files located in~/.claude/anthropic-docs/. These are routine operations for data retrieval. - [EXTERNAL_DOWNLOADS]: The skill references an official Anthropic documentation URL (
https://code.claude.com/docs/llms.txt) as the source for refreshing the local documentation mirror. This targets a well-known, trusted service. - [DATA_EXPOSURE]: The skill accesses files within the
~/.claude/directory. While this is in the user's home directory, the access is restricted to documentation files and a manifest, which is expected behavior for a tool designed to provide platform-specific reference material.
Audit Metadata