CVE-2026-18992: Incorrect Authorization in zhayujie CowAgent
CVE-2026-18992 is a medium severity vulnerability in zhayujie CowAgent versions 2.1.0 and 2.1.1. It involves incorrect authorization in the _select_tools function of the Self-Evolution Review Agent component, allowing remote attackers to manipulate authorization checks. Exploit code is publicly available, but no official patch or remediation has been confirmed.
AI Analysis
Technical Summary
This vulnerability affects zhayujie CowAgent up to versions 2.1.0 and 2.1.1. The flaw exists in the _select_tools function within the agent/evolution/executor.py file of the Self-Evolution Review Agent component. It allows an attacker to perform unauthorized actions remotely by manipulating authorization logic incorrectly. The CVSS 4.0 base score is 5.3 (medium severity), indicating network attack vector with low complexity and no user interaction required. Although exploit code is public, there is no vendor advisory or patch information available at this time.
Potential Impact
An attacker can remotely exploit this vulnerability to bypass authorization controls in the affected component, potentially leading to unauthorized actions within the CowAgent application. The impact is limited by the medium severity score and the requirement for some privileges (PR:L). There is no evidence of active exploitation in the wild.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the affected CowAgent versions 2.1.0 and 2.1.1 and monitor for suspicious activity related to the _select_tools function. Consider applying compensating controls to limit exposure.
CVE-2026-18992: Incorrect Authorization in zhayujie CowAgent
Description
CVE-2026-18992 is a medium severity vulnerability in zhayujie CowAgent versions 2.1.0 and 2.1.1. It involves incorrect authorization in the _select_tools function of the Self-Evolution Review Agent component, allowing remote attackers to manipulate authorization checks. Exploit code is publicly available, but no official patch or remediation has been confirmed.
CVSS v4.0
Score 5.3medium
Affected software
pkg:github/zhayujie/CowAgentcpe:2.3:a:zhayujie:cowagent:*:*:*:*:*:*:*:*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
This vulnerability affects zhayujie CowAgent up to versions 2.1.0 and 2.1.1. The flaw exists in the _select_tools function within the agent/evolution/executor.py file of the Self-Evolution Review Agent component. It allows an attacker to perform unauthorized actions remotely by manipulating authorization logic incorrectly. The CVSS 4.0 base score is 5.3 (medium severity), indicating network attack vector with low complexity and no user interaction required. Although exploit code is public, there is no vendor advisory or patch information available at this time.
Potential Impact
An attacker can remotely exploit this vulnerability to bypass authorization controls in the affected component, potentially leading to unauthorized actions within the CowAgent application. The impact is limited by the medium severity score and the requirement for some privileges (PR:L). There is no evidence of active exploitation in the wild.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the affected CowAgent versions 2.1.0 and 2.1.1 and monitor for suspicious activity related to the _select_tools function. Consider applying compensating controls to limit exposure.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-08-05T19:04:13.124Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a740d08bf8831d5391e5ec5
Added to database: 08/06/2026, 04:26:48 UTC
Last enriched: 08/06/2026, 04:44:32 UTC
Last updated: 08/06/2026, 04:50:43 UTC
Views: 4
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.