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 runid in the request body without ownership verification. The AgentCRUD.createtask and validatetaskcount functions look up the target AgentRun using the client-supplied runid without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid runid to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim's run.
{
"cwe_ids": [
"CWE-639"
],
"cna_assigner": "VulnCheck",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/65xxx/CVE-2026-65699.json"
}