CVE-2026-92360: Origin Validation Error in ag-ui-protocol ag-ui
A weakness has been identified in ag-ui-protocol ag-ui 1.0. The impacted element is the function prepareRunAgentInput of the file agent/agent.ts of the component Event Application Layer. This manipulation of the argument TEXT_MESSAGE_START causes origin validation error. Remote exploitation of the attack is possible. The pull request to fix this issue awaits acceptance.
AI Analysis
Technical Summary
This vulnerability affects ag-ui-protocol's ag-ui version 1.0, specifically the prepareRunAgentInput function in the agent/agent.ts file of the Event Application Layer component. The issue arises from improper origin validation due to manipulation of the TEXT_MESSAGE_START argument, which can be exploited remotely. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity. Although a pull request containing a fix exists, it has not yet been accepted or officially released.
Potential Impact
The vulnerability allows remote attackers to exploit an origin validation error, potentially leading to unauthorized actions or bypass of security controls related to origin checks. The CVSS vector indicates low complexity and no user interaction required, but limited privileges are needed. The impact includes limited confidentiality, integrity, and availability impacts. No known exploits are currently in the wild.
Mitigation Recommendations
A fix for this vulnerability has been developed but is not yet officially released. Users should monitor the vendor's repository or advisory channels for the acceptance of the pull request and apply the official patch once available. Until then, no official mitigation or workaround is confirmed.
CVE-2026-92360: Origin Validation Error in ag-ui-protocol ag-ui
Description
A weakness has been identified in ag-ui-protocol ag-ui 1.0. The impacted element is the function prepareRunAgentInput of the file agent/agent.ts of the component Event Application Layer. This manipulation of the argument TEXT_MESSAGE_START causes origin validation error. Remote exploitation of the attack is possible. The pull request to fix this issue awaits acceptance.
CVSS v4.0
Score 5.3medium
Affected software
ag-ui-protocol
ag-ui
pkg:github/ag-ui-protocol/ag-uicpe:2.3:a:ag-ui-protocol:ag-ui:*:*:*:*:*:*:*:*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 ag-ui-protocol's ag-ui version 1.0, specifically the prepareRunAgentInput function in the agent/agent.ts file of the Event Application Layer component. The issue arises from improper origin validation due to manipulation of the TEXT_MESSAGE_START argument, which can be exploited remotely. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity. Although a pull request containing a fix exists, it has not yet been accepted or officially released.
Potential Impact
The vulnerability allows remote attackers to exploit an origin validation error, potentially leading to unauthorized actions or bypass of security controls related to origin checks. The CVSS vector indicates low complexity and no user interaction required, but limited privileges are needed. The impact includes limited confidentiality, integrity, and availability impacts. No known exploits are currently in the wild.
Mitigation Recommendations
A fix for this vulnerability has been developed but is not yet officially released. Users should monitor the vendor's repository or advisory channels for the acceptance of the pull request and apply the official patch once available. Until then, no official mitigation or workaround is confirmed.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-09-16T05:36:05.161Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6aaa8fc855bf5e2cf59d7073
Added to database: 09/16/2026, 12:47:04 UTC
Last enriched: 09/16/2026, 13:01:39 UTC
Last updated: 09/17/2026, 03:34:44 UTC
Views: 15
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.