Openclaw cli: OpenClaw ACP client has permission auto-approval bypass via untrusted tool metadata (CVE-2026-32898)
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
Affected software
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
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.
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 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
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
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.