SkillSpector

—

Scan AI agent skills for vulnerabilities and malicious patterns.

PythonApache-2.0

Security scanner that statically analyzes AI agent skills for risks such as prompt injection, data exfiltration and supply-chain issues across dozens of vulnerability patterns, with optional LLM-based semantic review. Runs as a CLI or an MCP server to vet a skill before it is installed.

Does

Scan Analyze

Source code

For

DevSecOps Research