NVIDIA open-sources SkillSpector to scan AI agent skills for malicious code
dr_cintas · x · 2026-07-23
- NVIDIA’s SkillSpector is a free security scanner for AI agent skills used by tools like Claude Code, Codex CLI, and Gemini CLI.
- The pitch is simple: skills run with broad access, so a convenient skill can also leak secrets or introduce malicious behavior.
- SkillSpector can scan Git repos, URLs, zip files, directories, or single files, then produces a risk score from 0–100 with a verdict such as safe, caution, or do not install.
- It combines fast static analysis with an optional LLM-based semantic pass, checks live vulnerabilities via OSV.dev, and exports terminal/JSON/Markdown/SARIF reports.
- The repo claims coverage of 68 vulnerability patterns across 17 categories, including prompt injection, data exfiltration, privilege escalation, system prompt leakage, memory poisoning, MCP tool poisoning, and dangerous code.
- The screenshot also cites research saying 26.1% of skills contain vulnerabilities and 5.2% show likely malicious intent.
Related event: NVIDIA Open-Sources SkillSpector for AI Agent Security(3 posts)→
More from coding & agent
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11