CVE-2026-65699: low-severity vulnerability in reworkd AgentGPT
AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
28Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 2.3epss 0.3%
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.
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
Affected products
reworkd · AgentGPTpublic PoCs found — 1
cve_referencegithub.com/geo-chen/oss/blob/main/AgentGPT.mdunverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.