Vulnerability · Published Jul 23, 2026 · Assigned by VulnCheck

CVE-2026-65699AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation

Medium 4.2

In plain English

A medium-severity authorization bypass via user-controlled key in AgentGPT from reworkd. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 20% of all known vulnerabilities).

Severity (CVSS 3.1)4.2Medium

Exploit odds (30 days)0.3%top 79.9% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
reworkd	AgentGPT	0 – through 1.0.0

Weakness: CWE-639 · Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L

References

Researcher Disclosure technical-description, exploit
https://www.vulncheck.com/advisories/agentgpt-authorization-bypass-via-agent-task-creation third-party-advisory