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 ...
A semi-permeable barrier between your AI agent and the world. Scans and sanitizes untrusted content before it reaches your agent's context window. Zero external dependencies. Sub-5ms. Works offline.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results