claude-settings-audit
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard system discovery commands like
ls,find, andcatto identify the repository's tech stack and project structure. - [REMOTE_CODE_EXECUTION]: Recommends the installation of the Linear MCP server via
npx. This targets an official package from a well-known service and is documented as a user-configurable setting. - [DATA_EXFILTRATION]: Accesses project manifest files (e.g.,
package.json,pyproject.toml) and existing configuration files to provide tailored permission recommendations. No data is transmitted to external untrusted domains.
Audit Metadata