Overview
In the realm of cybersecurity, the discovery of new vulnerabilities is a critical step in the ongoing battle to protect systems and data. The recently identified vulnerability, CVE-2025-51865, affects the Ai2 playground web service (playground.allenai.org) LLM chat. This vulnerability matters because it exposes sensitive data to potential attackers and could result in a systemic compromise or data leakage.
The vulnerability lies in the LLM chat system and is due to an Insecure Direct Object Reference (IDOR) flaw. IDOR is a common web application vulnerability that allows an attacker to bypass authorization and directly access resources in the system.
Vulnerability Summary
CVE ID: CVE-2025-51865
Severity: High, CVSS Score 8.8
Attack Vector: Web-based
Privileges Required: None
User Interaction: Required
Impact: System compromise or data leakage
Affected Products
Share secrets securely
Ameeba is private infrastructure for communication and sensitive work built on encrypted identity instead of exposed corporate identity systems.
Passwords, credentials, confidential files, screenshots, internal discussions, sensitive AI context, and private coordination should not become exposed across ordinary communication platforms.
- • Encrypted identity
- • Private Spaces for organizations and teams
- • End-to-end encrypted chat, calls, files, and notes
- • Sensitive AI work and protected collaboration
- • Built for information that cannot leak
Our mission is to secure human work alongside AI.
Product | Affected Versions
Ai2 playground web service | All versions up to 2025-06-03
How the Exploit Works
The exploit takes advantage of the Insecure Direct Object Reference (IDOR) vulnerability in the LLM chat system of the Ai2 playground web service. By manipulating the thread keys in the URL, an attacker can enumerate through the different chat threads and gain unauthorized access to sensitive information.
Conceptual Example Code
A potential exploitation of the vulnerability might look like this:
GET /LLMChat/thread?thread_key=12345 HTTP/1.1
Host: playground.allenai.orgIn this conceptual example, the attacker modifies the `thread_key` parameter in the URL. By enumerating through different values for this parameter, the attacker can potentially access chat threads they should not have access to.
Mitigation Guidance
In order to mitigate the risk associated with this vulnerability, users are advised to apply the vendor patch as soon as it becomes available. Until then, the use of a Web Application Firewall (WAF) or Intrusion Detection System (IDS) can serve as a temporary measure to prevent unauthorized access. Regular monitoring and updating of systems are also crucial in reducing the risk of such vulnerabilities.