AI Agent Security

OWASP 2026 releases a brand-new security framework specifically designed for AI Agent systems, merging prompt injection and excessive agency into ASI01 Goal Hijack, covering ten attack surfaces including tool abuse, memory poisoning, and rogue agents - helping developers build complete protection mechanisms across input, tool, memory, and agent collaboration layers.

360’s security team found three critical OpenClaw vulnerabilities (CVSS up to 8.1) that let attackers bypass all tool permissions via prompt injection. 170K+ instances at risk, 340 malicious plugins on ClawHub. Here is what you need to patch now.