A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. Combines pattern-based detection (YAML + YARA), LLM-as-a-judge, and ...
Run sudo prove -r t after you have installed this module. The sudo is required because the test requires Nginx to listen on port 80. It can be built with Profile-Guided Optimization (PGO) using gcc ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results