LLM service interruption via uncapped page-state messages
Published Sep 2, 2026 · Updated Sep 3, 2026
Uncontrolled resource consumption in Open Browser at the affected commit allows context-dependent attackers to interrupt LLM service. The agent state-message path serializes untrusted DOM text and accessibility attributes, then sends the current message to model.invoke without enforcing its configured token budget. Exploitation requires the agent to interpret an attacker-controlled page; one oversized control can stall shared inference requests and pressure local memory and CPU.
Summary
What happened
Uncontrolled resource consumption in Open Browser at the affected commit allows context-dependent attackers to interrupt LLM service. The agent state-message path serializes untrusted DOM text and accessibility attributes, then sends the current message to model.invoke without enforcing its configured token budget. Exploitation requires the agent to interpret an attacker-controlled page; one oversized control can stall shared inference requests and pressure local memory and CPU.
The record
- CVE
- CVE-2026-84833
- Published
- Sep 2, 2026
- Updated
- Sep 3, 2026
- Vendor
- ntegrals
- Product
- Open Browser
- Classifications
- CWE-404, CWE-400, T1499
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 2, 2026CVE publishedPublication date reported by the CVE source.
- Sep 3, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=067fc45d649baa961750da8e2f4a75d87c5c75c8
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- OpenBrowser Message Budget DoS reproductionproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo