SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityDeferred

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.

LOW 2.3EPSS 0.28%

Does this matter?

Lower severity and a low EPSS score (0.28%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 4.0
2.3 LOWCVSS: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/M
EPSS
0.28% probability · 20th percentile
CISA KEV
Not listed
Weakness
CWE-639
Source
disclosure@vulncheck.com

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.