CVE-2026-65699 AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation
Authenticated users can attach tasks to other users' agent runs by supplying a target run_id, corrupting history and exhausting resources.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-65699?
CVE-2026-65699 is a low-severity missing authorization vulnerability in reworkd AgentGPT, published on 23 Jul 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim's run.
Weakness: CWE-639
Which versions are affected by CVE-2026-65699?
How do I fix CVE-2026-65699?
No fix has been published for CVE-2026-65699 yet. Limit exposure of the affected software until one is available.
Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.
Is CVE-2026-65699 being exploited?
There is no known exploitation of CVE-2026-65699 in the wild and no public exploit code.
Sources
Also known as GHSA-wwx9-477p-w7rm.