Openclaw cli: OpenClaw's Conflicting Tool Identity Hints Bypass Dangerous-Tool Prompting (CVE-2026-35655)
Description
A vulnerability in the openclaw CLI tool allowed conflicting tool identity hints from raw input and metadata to bypass dangerous-tool prompting, potentially enabling unsafe tool execution. This issue was fixed in version 2026.3.22 by enforcing a fail-closed behavior when conflicting tool identities are detected. The vulnerability has a medium severity with a CVSS score of 5.7.
CVSS v3.1
Score 5.7medium
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
The openclaw CLI's ACP permission resolution mechanism trusted conflicting tool identity hints from rawInput and metadata, which could suppress the dangerous-tool prompt that warns users about potentially unsafe tools. The vulnerability was addressed by changing the code to fail closed when meta, rawInput, and title tool identities conflict, rather than trusting spoofable raw input. This fix was introduced in version 2026.3.22 and remains in subsequent releases.
Potential Impact
An attacker could exploit this vulnerability to bypass the dangerous-tool prompt, potentially causing users to execute unsafe or malicious tools without warning. The impact is limited to integrity as per the CVSS vector, with no confidentiality or availability impact reported.
Mitigation Recommendations
A patch is available and was released in openclaw CLI version 2026.3.22. Users should upgrade to version 2026.3.22 or later to mitigate this vulnerability. No additional mitigation actions are required beyond applying the official fix.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- BREW-openclaw-cli-CVE-2026-35655
- Osv Schema Version
- 1.7.3
- Ecosystems
- ["Homebrew"]
- Cvss Version
- 3.1
Threat ID: 6ac245ab12601ec6a3166295
Added to database: 10/04/2026, 12:25:15 UTC
Last enriched: 10/04/2026, 12:54:11 UTC
Last updated: 10/04/2026, 16:08:37 UTC
Views: 2
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.