Snyk scanned 3,984 AI agent skills and found 13.4% with critical issues. Here is what malicious skills look like and the 7-check audit frame
{/* JSON-LD schema is generated server-side in app/blog/[slug]/page.tsx , do not
re-add an inline block here, it crashes<br>
MDX's Acorn parser on the leading <code>{</code>. */}</p>
<h2>
<a name="tldr" href="#tldr" class="anchor">
Certik Unveils ‘Anti-Virus for AI Agents’ as Skill Marketplaces Face Hidden Threats
Anthropic's Mythos AI model detects 23,000 vulnerabilities across 1,000 open source projects
Claude Mythos exposed a hard truth: Your enterprise patching process is way too slow
An AI skill is a Markdown file your coding agent reads and obeys. GitHub code search currently finds...
What It Is SkillSpector is a security scanner that analyzes AI agent skills...
CLI-Anything generates SKILL.md files that AI agents trust and execute. Snyk found 13.4% of agent skills contain critical…
The problem: 2,000 skills, no map Claude Code skills exploded across 2025 and into 2026....
A static AST scan of three open-source TypeScript agent codebases found 669 tool calls with real side effects. 553 had no guard…
A real-world implementation of static + LLM-based scanning for Claude Code / Cursor skill...
