SkillSpector
NVIDIA's open-source security scanner for agent skills. It checks Claude Code, Codex and MCP skills for vulnerabilities, prompt injection, data exfiltration and supply-chain risks before you install them, and it is part of the NVIDIA Verified Skills pipeline.
Updated
✨ Try AgentScout's free AI image generator →Good for: connecting tools with MCP, agent security and safety, security testing
Use cases
About SkillSpector
SkillSpector is listed in our security & governance category and is aimed at builders. NVIDIA's open-source security scanner for agent skills. It checks Claude Code, Codex and MCP skills for vulnerabilities, prompt injection, data exfiltration and supply-chain risks before you install them, and it is part of the NVIDIA Verified Skills pipeline. Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-11-05.
SkillSpector at a glance
- Category: Security & governance
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: NVIDIA/SkillSpector
- Official site: docs.nvidia.com/skills/scanning-agent-skills
- Listed on AgentScout: Nov 5, 2026
SkillSpector FAQ
What is SkillSpector?
NVIDIA's open-source security scanner for agent skills. It checks Claude Code, Codex and MCP skills for vulnerabilities, prompt injection, data exfiltration and supply-chain risks before you install them, and it is part of the NVIDIA Verified Skills pipeline.
How much does SkillSpector cost?
SkillSpector's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find SkillSpector's source code?
On GitHub at NVIDIA/SkillSpector.
What are alternatives to SkillSpector?
Similar tools include Snyk Agent Scan, Cisco MCP Scanner, HOL Guard, Pipelock, Marrow AI and Agent Control.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
SkillSpector ratings and reviews
Be the first to rate SkillSpector: tap 1 to 5 stars below. A written review is optional.
SkillSpector alternatives
Other security & governance tools in our directory. See all security & governance tools →
Snyk Agent Scan
Snyk's scanner for security risks in MCP servers and agent skills.
Cisco MCP Scanner
Cisco's open-source scanner that checks MCP servers and tools for malicious or risky behaviour using YARA rules and LLM analysis.
HOL Guard
HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards.
Pipelock
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action.
Marrow AI
Control layer for AI agents that checks policy, risk and prior outcomes before an agent acts, can require a named human yes, and keeps proof and outcome history; works with Claude Code, Codex, Cursor and MCP.
Agent Control
Agent Control's Action Gate is a Claude Code hook that makes the agent ask before a Slack post, a CRM edit or a deploy; a no, or no answer in 10 minutes, stops the tool call. Connect adds ask-before-paying controls for agent payments. Action Gate is $49 for 30 days, paid in USDC on Base, Solana or Ethereum.
Get your badge
Built SkillSpector? Optional. Showing this badge does not change your rank or earn a Featured spot. It links to this page. About badges