PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-92360 ag-ui-protocol CVE debrief

A weakness has been identified in ag-ui-protocol ag-ui 1.0, specifically in the prepareRunAgentInput function of the agent/agent.ts file. This issue causes an origin validation error when manipulating the TEXT_MESSAGE_START argument. Remote exploitation is possible, but the extent of impact and affected versions require verification from official sources.

Vendor
ag-ui-protocol
Product
ag-ui
CVSS
MEDIUM 5.3
CISA KEV
Not listed in stored evidence
Original CVE published
2026-09-16
Original CVE updated
2026-09-22
Advisory published
2026-09-16
Advisory updated
2026-09-22

Who should care

Defenders responsible for ag-ui-protocol ag-ui deployments should assess exposure and prioritize verification of inventory and potential impact. This includes operators, platform administrators, vulnerability management teams, and security teams who need to verify the presence of ag-ui-protocol ag-ui 1.0 in their environment, assess the potential impact of the vulnerability, and prioritize remediation or compensating controls. They should also monitor for

Why it matters

CVE-2026-92360 is a weakness in ag-ui-protocol ag-ui 1.0 that allows for remote exploitation. Defenders should verify exposure, assess potential impact, and prioritize remediation or compensating controls.

  • Verify exposure to remote exploitation
  • Assess potential impact on affected systems
  • Prioritize remediation or compensating controls
  • Monitor for official vendor remediation

Technical summary

The prepareRunAgentInput function in agent/agent.ts of ag-ui-protocol ag-ui 1.0 is vulnerable to origin validation error when manipulating the TEXT_MESSAGE_START argument. This weakness allows for remote exploitation. The issue is located in the Event Application Layer. Defenders should prioritize verifying the presence of this vulnerability in their inventory and assessing exposure, given the potential for remote exploitation. The extent of impact and affected versions require verification from official sources. The CVE record and NVD entry provide details on the vulnerability, but evidence is limited regarding affected versions, exploitation, and impact.

Defensive priority

Defenders should prioritize verifying the presence of this vulnerability in their inventory and assessing exposure, given the potential for remote exploitation.

Recommended defensive actions

  • Verify the presence of ag-ui-protocol ag-ui 1.0 in your inventory
  • Assess exposure to the prepareRunAgentInput function vulnerability
  • Monitor for official vendor remediation or compensating controls
  • Consider exception tracking for unremediated instances
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record and NVD entry provide details on the vulnerability, but evidence is limited regarding affected versions, exploitation, and impact. Official sources indicate a pull request to fix this issue awaits acceptance.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-92360 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-92360

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-92360 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-92360

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.