Separation of Duties for Privileged LLM Agents: A Governed Execution Architecture with Measured Security-Utility Trade-Offs

Large language model agents are increasingly granted real privileges executing commands, modifying files, calling APIs, so an agent that errs has already acted. Existing defences concentrate on the agent's inputs, while the path from a candidate action to privileged side effects remains less...

Duplicate Advisory: OpenClaw has an improper sandbox configuration vulnerability

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-43x4-g22p-3hrq. This link is maintained to preserve external references. Original Description OpenClaw versions prior to 2026.2.21 contain an improper sandbox configuration vulnerability that allows attackers to...

EUVD-2026-13941

OpenClaw versions prior to 2026.2.21 contain an improper sandbox configuration vulnerability that allows attackers to execute arbitrary code by exploiting renderer-side vulnerabilities without requiring a sandbox escape. Attackers can leverage the disabled OS-level sandbox protections in the...

CVE-2026-32046

CVE-2026-32046 involves OpenClaw prior to 2026.2.21 with an improper sandbox configuration that lets an attacker run arbitrary code by exploiting renderer-side vulnerabilities without sandbox escape. The exploit leverages disabled OS-level sandbox protections inside the Chromium browser container...