OpenClaw before 2026.4.10 contains an input validation vulnerability that allows external hook metadata to be enqueued as trusted system events. Attackers can supply malicious hook names to escalate untrusted input into higher-trust agent context.Creditszsx (@zsxsoft)qclawerKeenSecurityLabReferenceshttps://github.com/openclaw/openclaw/security/advisories/GHSA-7g8c-cfr3-vqqrhttps://github.com/openclaw/openclaw/commit/e3a845bde5b54f4f1e742d0a51ba9860f9619b29https://www.vulncheck.com/advisories/openclaw-unsanitized-external-input-in-agent-hook-events