Cross-user task writes via unchecked run ownership
Published Jul 23, 2026 · Updated Jul 23, 2026
Authorization bypass in Reworkd AgentGPT 1.0.0 and earlier allows remote authenticated users to attach tasks to another user's run. AgentCRUD.create_task and validate_task_count fetch the client-selected AgentRun by run_id without comparing its user_id with the session user. Exploitation requires a valid, normally unexposed UUID; successful writes corrupt task history, consume the run's loop budget, and charge LLM use without disclosing data.
Summary
What happened
Authorization bypass in Reworkd AgentGPT 1.0.0 and earlier allows remote authenticated users to attach tasks to another user's run. AgentCRUD.create_task and validate_task_count fetch the client-selected AgentRun by run_id without comparing its user_id with the session user. Exploitation requires a valid, normally unexposed UUID; successful writes corrupt task history, consume the run's loop budget, and charge LLM use without disclosing data.
The record
- CVE
- CVE-2026-65699
- Published
- Jul 23, 2026
- Updated
- Jul 23, 2026
- Vendor
- Reworkd
- Product
- AgentGPT
- Classifications
- T1565.001
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 23, 2026CVE publishedPublication date reported by the CVE source.
- Jul 23, 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=0 <=1.0.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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
No public exploit references are available in this record.
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