CVE-2026-65699 — AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation
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 …
Published: 2026-07-23 · CVSS: 2.3 · CVSS 4.0
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7