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, and MCP skills before you install them.
1 skill listed · Apache 2.0 · 22.8k stars · last pushed 27 Oct 2026
NVIDIA/SkillSpector on GitHub (opens in a new tab)Skills
| Skill | Check | Capabilities | Licence | Updated |
|---|---|---|---|---|
| skill-inspector Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious. Pattern check: Nothing flaggedWhat it can touch: Runs shell commandsApache 2.0 · Updated 8 Oct 2026 | Pattern check: Nothing flagged | What it can touch: Runs shell commands | Apache 2.0 | 8 Oct 2026 |
Not listed from this repo
32 test fixtures.