One command turns any open-source repo into an AI agent backdoor. OpenClaw proved no supply-chain scanner has a detection category for it

CLI-Anything generates SKILL.md files that AI agents trust and execute. Snyk found 13.4% of agent skills contain critical security issues. No SAST or SCA scanner detects malicious instructions at the agent integration layer. Three-layer audit framework and five-step action plan for security directors.

Raccontata datheregister.comventurebeat.com