CVE-2026-65699

What it is

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.

At a glance

Exploitability

Can be exploited over the network with a low-privilege account. Limited direct impact.

Exploit odds

0.3% chance of exploitation in the next 30 days (EPSS).

Fix

No patch or advisory is linked yet. Look at mitigations or restrict exposure.

Timeline

1. 2026-07-23 18:17 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-24 13:10 UTC Last updatedMost recent change to the record

Details

Published

2026-07-23 18:17 UTC

Last modified

2026-10-24 13:10 UTC

Exploit probability

0.3% · EPSS, next 30 days

Weakness

CWE-639 · Insecure direct object reference

Record status

Deferred

Attack profile CVSS 4.0 · 2.3

Attack vector

Network

Complexity

High

Attack requirements

None

Privileges needed

Low

User interaction

None

Confidentiality

None

Integrity

Low

Availability

Low