Openclaw cli: OpenClaw: Agentic Consent Bypass — LLM Agent Can Silently Disable Exec Approval via `config.patch` (CVE-2026-41349)
Description
A high-severity vulnerability (CVE-2026-41349) in the openclaw-cli package allows a large language model (LLM) agent to bypass agentic consent by silently disabling execution approval via the config.patch mechanism. This issue affects versions from 2026.1.29 up to but not including 2026.3.28. The vulnerability has been fixed in version 2026.3.28 and later.
CVSS v4.0
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 package contained a vulnerability where an LLM agent could bypass the expected execution approval process by manipulating the config.patch setting, effectively disabling exec approval silently. This agentic consent bypass was identified and fixed by the maintainers in commit 76411b2afc4ae721e36c12e0ea24fd23e2fed61e on 2026-03-27, with the fix included starting in version 2026.3.28. Versions from 2026.1.29 up to but excluding 2026.3.28 are vulnerable.
Potential Impact
An attacker or automated agent with limited privileges could disable execution approval controls silently, potentially allowing unauthorized or unintended command execution without user consent. This could undermine security controls designed to prevent unauthorized actions by the LLM agent.
Mitigation Recommendations
Users should upgrade openclaw-cli to version 2026.3.28 or later, where the vulnerability has been fixed. The maintainers have confirmed the fix is available and shipped. No additional mitigation steps are indicated beyond applying the official update.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- BREW-openclaw-cli-CVE-2026-41349
- Osv Schema Version
- 1.7.3
- Ecosystems
- ["Homebrew"]
- Cvss Version
- 4.0
Threat ID: 6ac245a312601ec6a3165d95
Added to database: 10/04/2026, 12:25:07 UTC
Last enriched: 10/04/2026, 12:49:40 UTC
Last updated: 10/04/2026, 16:08:38 UTC
Views: 3
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.