Skip to main content
EPSS 0.3%top 74%

Openclaw cli: OpenClaw ACP client has permission auto-approval bypass via untrusted tool metadata (CVE-2026-32898)

0
Medium
Published: 08/13/2026 (08/13/2026, 17:21:32 UTC)
Source: GCVE Database
Product: openclaw-cli

Description

The OpenClaw ACP client had a vulnerability allowing auto-approval of tool calls based on untrusted metadata and permissive name heuristics. This flaw could let a malicious or compromised tool bypass interactive approval prompts for read-class operations. The issue was fixed in version 2026.2.23 by requiring trusted core tool IDs for auto-approval and scoping read approvals more strictly.

CVSS v3.1

Score 5.4medium

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
Low
Availability
None
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N

Affected software

Homebrewmore threats →ghsa
openclaw-cli
pkg:brew/openclaw-cli
Affected versions
>=2026.1.29 <2026.2.23

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 10/04/2026, 13:00:46 UTC

Technical Analysis

CVE-2026-32898 affects the OpenClaw ACP client (npm package openclaw) versions from 2026.1.29 up to but not including 2026.2.23. The vulnerability arises because the client trusted incoming toolCall.kind metadata and used heuristic name matching to auto-approve permission requests. Non-core read-like names and spoofed kind metadata could bypass interactive approval prompts for read operations. The fix involved ignoring untrusted toolCall.kind values, requiring trusted core tool IDs for auto-approval, scoping read auto-approval to current working directory resolved paths, and adding stricter tool-name validation.

Potential Impact

An attacker controlling or compromising an ACP tool invocation could bypass expected interactive permission approval prompts for read-class operations, potentially allowing unauthorized read access. The CVSS 3.1 score is 5.4 (medium severity), reflecting network attack vector, low attack complexity, low privileges required, no user interaction, and limited confidentiality and integrity impact without availability impact.

Mitigation Recommendations

A patch is available and was released in version 2026.2.23. Users should upgrade to version 2026.2.23 or later to remediate this vulnerability. The fix removes reliance on untrusted metadata for auto-approval and enforces stricter validation and scoping of read permissions.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Gcve Source
db.gcve.eu
Osv Id
BREW-openclaw-cli-CVE-2026-32898
Osv Schema Version
1.7.3
Ecosystems
["Homebrew"]
Cvss Version
3.1

Threat ID: 6ac245b612601ec6a3166bbe

Added to database: 10/04/2026, 12:25:26 UTC

Last enriched: 10/04/2026, 13:00:46 UTC

Last updated: 10/04/2026, 16:08:37 UTC

Views: 1

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses