ConfirmedA court, a regulator or the organization itself has stated the core facts, or the record cites a court or regulator source.
Ant Group AI lab finds 8 vulnerabilities in OpenClaw autonomous agent framework
Ant Group's AI Security Lab audited the OpenClaw autonomous agent framework and found 33 security vulnerabilities, with 8 patched in the latest release including critical and high-risk flaws.
AII-1000-644533 sources ↓
What happened
Ant Group's AI Security Lab conducted a three-day security audit of the open-source autonomous intelligent agent framework OpenClaw and submitted 33 security vulnerability reports.
OpenClaw version 2026.3.28 confirmed and patched 8 vulnerabilities: 1 critical severity, 4 high-risk, and 3 medium-risk.
Governance controls
Ant Group stated it would continue monitoring OpenClaw's security risks to support the industry in securely and stably applying AI agents.
Classification
Sources and evidence
This record was researched and written by the Index, based on the following original reporting.
guancha.cn
Ant Group AI lab finds 8 vulnerabilities in OpenClaw autonomous agent framework
30 March 2026