CVE-2026-65699

published 23 Jul 2026 · updated 23 Jul 2026

AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation

5.2MediumCVSS 4.2EPSS 0%1 public exploits

A public exploit exists; no exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. No fixed version is recorded.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
reworkd<=1.0.0

Exploit evidence

1 public sources

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-65699 severity on Zeptric[![CVE-2026-65699](https://zeptric.io/badge/cve/CVE-2026-65699.svg)](https://zeptric.io/cve/CVE-2026-65699)