Skip to main content
VulnerabilityPublished Updated

Openclaw cli: OpenClaw's non-default autoAllowSkills setting could bypass on-miss exec prompt

Affects openclaw-cliSource GCVE Database

0

CVSS 7.3 High : upgrade to 2026.2.23 soon.

Data as of 17 Nov 2026, 19:05 UTC

CVSS 4.0 base score
7.3High
How severe the flaw is on the 0–10 CVSS scale.
Patch
Available – fixed in 2026.2.23
CVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

What to do

Upgrade openclaw-cli to 2026.2.23.

Affected software

ProductAffectedFixed in
Homebrewopenclaw-clipkg:brew/openclaw-cliOther threatsAffected
  • >=2026.1.29 <2026.2.23
Fixed in
  • 2026.2.23

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A patch is available and should be applied by upgrading to openclaw CLI version 2026.2.23 or later. This update hardens the allowlist matching logic to prevent bypass of the on-miss execution prompt. Users with the default configuration (autoAllowSkills=false) are not affected and no action is required.

Description

OpenClaw CLI versions up to 2026.2.22-2 contain a vulnerability in a non-default configuration where the autoAllowSkills setting is enabled. This flaw allows a skill-name collision to bypass the 'ask=on-miss' execution approval prompt, potentially permitting execution without operator confirmation. The issue arises because the allowlist evaluator matches skill names by basename, allowing path-scoped executables to bypass prompts. The vulnerability is fixed in version 2026.2.23 by requiring pathless invocation tokens and trusted resolved executable paths for auto-allow matching.

References

Community reviews

Loading reviews…