agent-owasp-check
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a series of PowerShell and git-grep commands to identify potential security risks in source code. These commands are used for pattern matching against common vulnerabilities like privilege escalation, prompt injection, and data exfiltration. The use of these commands is consistent with the skill's stated purpose as a security auditing tool.
- [REMOTE_CODE_EXECUTION]: The skill includes an optional step to run the 'mcp-scan' tool using 'uvx'. This involves downloading and executing a Python package. The package is pinned to a specific version ('0.1.14') and originates from a reputable security-focused organization, which is appropriate for a security auditing workflow.
- [DATA_EXFILTRATION]: The skill contains patterns to search for sensitive data leaks (e.g., secrets in logs) but does not perform any network operations to exfiltrate data itself.
Audit Metadata