4 projects
skillscan-fuzzer
LLM-powered adversarial skill file fuzzer for skillscan-security
skillscan-trace
Behavioral execution engine for MCP-based AI agent skills
skillscan-lint
Quality linter for AI agent skill files — readability, clarity, and graph integrity checks
skillscan-security
Standalone AI skill security scanner — detects prompt injection, tool poisoning, and supply-chain attacks in MCP skills
