Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-65699— AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation

Quick assessment

Affected
reworkd AgentGPT
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Reworkd AgentGPT是美国Reworkd公司的一个AI智能体开发平台。 Reworkd AgentGPT 1.0.0及之前版本存在授权问题漏洞，该漏洞源于用户可控密钥的授权绕过问题，允许认证用户在请求体中提供目标run_id而不进行所有权验证，从而导致攻击者能够附加任务到其他用户的agent运行，破坏任务历史、耗尽每运行循环预算并增加LLM成本。

CVSS 4.2 · Medium EPSS 0.28% · P18

Possible ATT&CK Techniques 1 AI

T1078.001 · Default Accounts

Affected Version Matrix 1

VendorProduct Version RangeStatus
reworkd AgentGPT ≤ 1.0.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-65699

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
AgentGPT 1.0.0 Authorization Bypass via Agent Task Creation
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
通过用户控制密钥绕过授权机制
Source: CVE Program / CVE List V5
Vulnerability Title
Reworkd AgentGPT 授权问题漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Reworkd AgentGPT是美国Reworkd公司的一个AI智能体开发平台。 Reworkd AgentGPT 1.0.0及之前版本存在授权问题漏洞，该漏洞源于用户可控密钥的授权绕过问题，允许认证用户在请求体中提供目标run_id而不进行所有权验证，从而导致攻击者能够附加任务到其他用户的agent运行，破坏任务历史、耗尽每运行循环预算并增加LLM成本。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
reworkd AgentGPT 0 ~ 1.0.0 -

II. Public POCs for CVE-2026-65699

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-65699

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-65699 (1)

Other References for CVE-2026-65699 (1)

IV. Related Vulnerabilities

Same weakness: CWE-639

V. Comments for CVE-2026-65699

No comments yet

Leave a comment