CyberRota Analysis
AI-GeneratedAgentGPT versions up to 1.0.0 are vulnerable to an authorization bypass that allows authenticated users to manipulate another user's agent run by supplying a valid run_id without proper ownership verification. This flaw can lead to unauthorized task attachment, potentially corrupting task history and exhausting resource budgets, resulting in increased operational costs for the affected user. Organizations using AgentGPT should prioritize patching this vulnerability to prevent exploitation and protect their resources.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD 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.