search-files
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or security bypass attempts were identified.
- [COMMAND_EXECUTION]: The skill utilizes standard tools like Grep and Glob for their intended purpose of searching file contents and names.
- [DATA_EXPOSURE]: Access to
memory/file_index.mdis required for the skill to function as a search index and does not involve exfiltrating sensitive data. - [PROMPT_INJECTION]: The instructions are purely functional and do not attempt to override the AI agent's core safety protocols or system prompts.
Audit Metadata