← All Advisories

OpenClaw exec approval policy bypass lets an agent run arbitrary host commands without re-prompting

Last refreshed2026-09-30

Status: NEW  |  Advisory ID: CVE-2026-100561

Key Details

CVECVE-2026-100561
CVSS Score / Version8.0 (High) / CVSS v3.1
Updated2026-09-26
CVSS VectorCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H
CVSS Proseattack vector is network; attack complexity is low; privileges required is low; user interaction is required; scope is unchanged; confidentiality impact is high; integrity impact is high; availability impact is high.
Classified asCWE-88 (Improper Neutralization of Argument Delimiters in a Command ('Argument Injection'))

What to Know

OpenClaw (npm package 'openclaw') versions >= 2026.3.22 and < 2026.8.1 contain an approval-bypass flaw in the exec approval policy: the policy could trust a command-running wrapper without inspecting the command carried in its arguments. After an operator allowlisted or permanently approved a benign wrapper invocation, a later agent turn could substitute an arbitrary inner command and execute it with the OpenClaw process's host privileges without a further approval prompt. Exploitation requires the relevant wrapper to resolve on the host and a prior operator decision allowing that wrapper. Transparent shell carriers and opaque utilities such as process monitors, tracers, namespace tools, and proxy wrappers were affected through related trust-resolution gaps. Fixed in 2026.8.1. (NVD)

References

SourceReference
NVDhttps://nvd.nist.gov/vuln/detail/CVE-2026-100561
CVEhttps://www.cve.org/CVERecord?id=CVE-2026-100561