⬢github first seen 1 d ago, last 6 h ago, peak #7

NVIDIA releases SkillSpector security scanner for AI agent skills

Original: NVIDIA/SkillSpector

NVIDIA has published SkillSpector, an open-source security scanner for AI agent skills. The Python tool detects vulnerabilities, malicious patterns, prompt injection, data exfiltration and supply-chain risks in skills for Claude Code, Codex and MCP before they are installed. The release is drawing attention as adoption of third-party agent skills grows and developers look for ways to vet them before use.

Why now: Rapid growth of third-party AI agent skills has created fresh security concerns that this tool addresses.

NVIDIASkillSpectorClaude CodeCodexMCP

Open on github →

Evidence

• NVIDIA/SkillSpector · NVIDIA · 16

  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.

API: https://socialmediatrends-api.osmike.com/v1/trends/3732143