NVIDIA/SkillSpector: Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex
Why CEREBRO kept it
Security scanner for Claude Code and Codex agent skills
The text below is an automated extraction of the article at https://github.com/NVIDIA/SkillSpector, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. AI agent skills (used by Claude Code, Codex CLI, Gemini CLI, etc.) execute with implicit trust and minimal vetting. In the 31,132-skill analyzed subset of the research dataset, 26.1% of skills contain vulnerabilities and 5.2% show likely malicious intent. SkillSpector helps you answer: "Is this skill safe to install?" SkillSpector is part of the NVIDIA Verified Skills pipeline, which scans, evaluates, and signs agent skills before publication. Skills that pass ar
Backlinks
Appeared in 1 briefing