manage-skills
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands (ls, mkdir, cat, mv, rm, find, grep) to manage configuration files and directories associated with various AI tools in user-controlled paths such as ~/.cursor/skills/ and ~/.claude/skills/.
- [SAFE]: No malicious patterns such as remote code execution, unauthorized data exfiltration, or obfuscated payloads were identified. The described operations are consistent with the skill's stated purpose of managing local agent instructions and rules.
Audit Metadata