CVE-2026-65699

AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation

Published Jul 23, 2026 CVSS 4.0 · 2.3 Low EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

AgentGPT 1.0.0 contains an authorization bypass that allows any authenticated user to create tasks for another user's agent run by providing a target run_id in the request body. The internal functions that create a task and enforce the per‑run loop budget do not verify that the supplied run_id belongs to the requester, enabling an attacker with valid credentials and knowledge of a run_id to corrupt task history, exhaust the run’s loop budget, and force the victim’s account to incur additional large language model usage costs. This flaw is classified as CWE‑639.

Affected Systems

The affected product is reworkd:AgentGPT, all releases up through version 1.0.0. The vulnerability is present in every deployment of 1.0.0 or earlier; newer releases are assumed remedied unless proven otherwise.

Risk and Exploitability

The CVSS score of 2.3 signals low severity while the EPSS score of less than 1% indicates that exploit attempts are expected to be rare. The vulnerability is not listed in CISA’s KEV catalog. The likely attack vector is an authenticated API call that includes a target run_id in the request body; the attacker merely needs valid credentials and knowledge of a valid run_id to abuse the endpoint.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade AgentGPT to a patched release (e.g., version 1.1 or later) which corrects the run_id ownership validation.
  • If a vendor fix is not yet available, restrict access to the task‑creation API by allowing only trusted internal IPs or network segments, or enforce an additional layer that verifies the run_id belongs to the authenticated user before creating the task.
  • Enable monitoring of task-creation logs and alert on unusual activity, such as repeated task additions with the same run_id from unexpected users.

Generated by OpenCVE AI on August 3, 2026 at 21:15 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
First Time appeared Reworkd
Reworkd agentgpt
Vendors & Products Reworkd
Reworkd agentgpt
Type Values Removed Values Added
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.
Title AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation
Weaknesses CWE-639
References
Metrics cvssV3_1

{'score': 4.2, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L'}

cvssV4_0

{'score': 2.3, 'vector': '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'}

ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Weaknesses
  • CWE-639

    Authorization Bypass Through User-Controlled Key

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Jul 23, 2026, 6:17 PM
Reserved
Jul 22, 2026, 8:26 PM
Status
Deferred
Published
Jul 23, 2026, 6:17 PM
Modified
Oct 24, 2026, 1:10 PM