A
licenseNot graded
qualityA
maintenanceEnables scanning of AI agent code for security vulnerabilities such as prompt injection, tool abuse, and data exfiltration, directly from MCP-compatible clients like Claude Code.
2
LGPL 3.0
No user-submitted related servers found.
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool has a clearly distinct purpose.
With a single tool, naming consistency is perfect by definition. 'scan_skill' follows a clear verb_noun pattern.
One tool is below the typical 3-15 range, but it is appropriate for a focused security scanner. A single comprehensive tool suffices for the stated purpose.
The tool covers all listed malware patterns (secret exfiltration, install hooks, obfuscated execution, prompt injection, committed binaries, auto-approve configs) with a static approach. No obvious gaps within its scope.