Auth bypass in Reworkd Agentgpt
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.
Vulnerability class: IDOR (Insecure Direct Object Reference)
EPSS: 0.003 (19.7th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 4.2 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L.
Affected products
- Reworkd Agentgpt — versions 0
Weakness classification (CWE)
References
- disclosure@vulncheck.com (technical-description, exploit)
- disclosure@vulncheck.com (third-party-advisory)
Frequently asked questions
- What is CVE-2026-65699?
- CVE-2026-65699 is a medium-severity vulnerability in Reworkd Agentgpt, classified under Authorization Bypass Through User-Controlled Key. CVSS score: 4.2/10. Published 2026-07-23.
- How severe is CVE-2026-65699?
- Medium severity. CVSS v3 base score is 4.2 out of 10.