Leading agent security scanner. Auto-discovers Claude, Cursor, Gemini CLI, Windsurf configs. Skill Inspector (Feb 2026) scans individual skills. Snyk+Vercel partnership extends supply chain trust.
Snyk Agent Scan
activeBest overall agent security scanner. 1,929 stars. Scans AI agents, MCP servers, and skills for prompt injection, tool poisoning, toxic flows. Auto-discovers Claude, Cursor, Gemini CLI, Windsurf configs. Skill Inspector launched Feb 2026. Snyk+Vercel supply chain partnership.
Where it wins
Scans AI agents, MCP servers, and skills — purpose-built for the agent security surface
Auto-discovers Claude, Cursor, Gemini CLI, Windsurf configurations
Skill Inspector launched Feb 2026 — inspects individual skills/tools
Snyk+Vercel supply chain partnership — extending trust chain
Enterprise trust — Snyk brand carries weight in security-conscious orgs
1,929 stars — strong early adoption
Where to be skeptical
Commercial — requires Snyk platform
Relatively new category — agent security scanning is still maturing
Editorial verdict
#1 agent/MCP security scanner. Scans AI agents, MCP servers, and skills for prompt injection, tool poisoning, and toxic flows. Auto-discovers Claude, Cursor, Gemini CLI, Windsurf configs. Skill Inspector (Feb 2026) + Vercel supply chain partnership. Enterprise trust.
Related

CodeQL (via GitHub MCP Server)
88GitHub-native SAST via CodeQL, accessible through the official GitHub MCP Server. Copilot Autofix generates fixes from CodeQL alerts. GitHub Security Lab Taskflow Agent found ~30 real CVEs. Zero extra setup for GitHub users.

TruffleHog
8818K+ stars. 800+ secret types. Unique credential verification — confirms if leaked creds are still active. Scans S3, Docker, Slack — not just git. No official MCP but community integrations exist.
Gitleaks
8824.4K stars — most-starred secret scanner. 150+ patterns. Fastest pre-commit scanner. The community default for pre-commit secret detection. No official MCP.

Tencent AI-Infra-Guard
81Most comprehensive OSS AI red teaming tool. 3,264 stars. Full-stack: ClawScan, Agent Scan, Skills Scan, MCP scan, jailbreak eval. 43 AI framework components, 589 CVEs cataloged. v4.0 released.
Public evidence
Supply chain partnership extending agent security to Vercel deployment pipeline. Enterprise validation of agent security scanning as a category.
Raw GitHub source
GitHub README could not be fetched right now.