vetting-agent-extensions
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides defensive guidelines and methodology for auditing agent extensions, MCP servers, and plugins. It does not contain any executable code or malicious instructions.
- [EXTERNAL_DOWNLOADS]: The instructions recommend using a third-party markdown conversion service (defuddle.md) for token optimization when reading external advisories. The skill includes appropriate warnings regarding the privacy risks of routing data through a third-party service.
Audit Metadata