Nvidia Introduces SkillSpector With 64 Security Checks for AI Agent Skills
Nvidia has introduced SkillSpector, a security scanner designed to scan AI agent skills before installation. The tool runs 64 security checks across 16 categories and combines fast static analysis with optional LLM semantic evaluation, including prompt injection detection, credential theft detection, supply-chain vulnerability scanning, AST and taint-flow analysis, MCP security checks and SARIF output for CI/CD.
From the sources (2 posts)
@nptacekRT @bibryam: SkillSpector - a new security scanner for skills by NVIDIA • Scan AI agent skills before installing them • 64 security checks…
@bibryamSkillSpector - a new security scanner for skills by NVIDIA • Scan AI agent skills before installing them • 64 security checks across 16 categories • Fast static analysis + • Optional LLM semantic evaluation • Prompt injection detection • C