crw-best-practices
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official documentation and repositories located at
fastcrw.comandgithub.com/us/crw. These are vendor-owned resources associated with the skill author. - [COMMAND_EXECUTION]: The documentation provides examples for using the
crwcommand-line interface and suggests using Python subprocesses to filter search results before they enter the agent's context. This is a documented best practice for maintaining context hygiene. - [CREDENTIALS_UNSAFE]: The skill mentions the requirement of API keys for REST API usage but correctly utilizes non-functional placeholder strings (e.g.,
crw_live_...) in its examples. - [DATA_EXFILTRATION]: The skill describes functionality for fetching data from external URLs via scraping and searching. However, these are the primary intended functions of the tool, and the skill includes instructions on how to handle and filter this data safely using local subprocesses.
Audit Metadata