CVE-2026-41349
OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent.
View on NVDAnalysis
The vulnerability affects OpenClaw, an LLM agent framework, allowing agents to bypass execution approvals and perform unauthorized operations. While the high severity is notable, OpenClaw is not a core part of the standard web or backend development stack used by the community.
Severity
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HCWE-862EPSS
Affects
openclaw:openclawTechnical description
OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent.