AgentGPT authorization bypass allows unauthorized task attachment
AgentGPT through version 1.0.0 contains an authorization bypass vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target run_id without ownership verification. Attackers can corrupt task history, exhaust loop budgets, and drive LLM costs against victims.
Disclosed 23 July 2026 · Record updated 13 September 2026
Impact
Authenticated attackers can attach tasks to other users' agent runs, corrupting task history, exhausting per-run loop budgets, and increasing LLM costs for victims.
Our coverage
No articles linked to this incident yet.
Sources
- nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-65699
