CVE-2026-65699

MEDIUMCVSS 4.2/10

Last modified

CVE-2026-65699 is a medium-severity vulnerability rated 4.2/10 on the CVSS scale. 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..

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.

Metrics

CVSS 3.1
4.2/10

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L

CVSS 4.0
2.3/10

CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Weakness Enumeration

Affected Software

Source: CNA advisory (CVE.org). NVD analysis pending.

VendorProductVersions
reworkdAgentGPT<= 1.0.0

References

Timeline

Published
Last Modified
Status
Deferred

Frequently Asked Questions

What is CVE-2026-65699?
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.
How severe is CVE-2026-65699?
CVE-2026-65699 has a CVSS score of 4.2/10 (MEDIUM severity).
How do I fix CVE-2026-65699?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

Are you affected by CVE-2026-65699?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST