CVE-2026-65699

MediumCVSS 4.2

Published: 23/07/2026(UTC)Updated: 23/07/2026(UTC)Translated: 25/07/2026(UTC)NVD NIST

Exploitation Probability (EPSS)

Low risk

0.22%

13th percentile - higher than 13% of all known CVEs

Summary

AgentGPT through 1.0.0 contains an authorization bypass vulnerability allowing authenticated users to attach tasks to another user's agent run by supplying a run_id without ownership verification.

Risk Assessment

An attacker can corrupt task history, exhaust loop budget, and drive LLM costs against the victim's run, leading to disruption and financial loss.

Recommendation

Upgrade AgentGPT to a version beyond 1.0.0 if available, or apply a patch that verifies run_id ownership.

Other vulnerabilities in AgentGPT

CVE-2026-51867Critical
agentgpt v.1.0.0 is vulnerable to Incorrect Access Control in next/src/server/api/routers/agentRouter.ts. An externally reachable path accepts a caller-selected object or tenant identifier and reaches a data-access operation without a visible owner, tenant, workspace, or membership binding on that object.

Original NVD description (English source)

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 data from NVD (NIST) · CISA KEV · EPSS