CVE-2025-51865

HIGH

Ai2 Playground <2025-06-03 - Info Disclosure

Title source: llm
STIX 2.1

Exploitation Summary

EIP tracks 1 public exploit for CVE-2025-51865. PoCs published by Secsys-FDU.

AI-analyzed exploit summary The repository describes an Insecure Direct Object Reference (IDOR) vulnerability in Ai2's playground web application, allowing attackers to brute-force conversation message IDs to access other users' chat histories. The attack vector relies on predictable message ID formats (e.g., `msg_A1A1A1A1A1`).

Description

Ai2 playground web service (playground.allenai.org) LLM chat through 2025-06-03 is vulnerable to Insecure Direct Object Reference (IDOR), allowing attackers to gain sensitvie information via enumerating thread keys in the URL.

Exploits (1)

nomisec WRITEUP 2 stars
by Secsys-FDU · poc
https://github.com/Secsys-FDU/CVE-2025-51865

The repository describes an Insecure Direct Object Reference (IDOR) vulnerability in Ai2's playground web application, allowing attackers to brute-force conversation message IDs to access other users' chat histories. The attack vector relies on predictable message ID formats (e.g., `msg_A1A1A1A1A1`).

Classification
Writeup 90%
Attack Type
Info Leak
Complexity
Trivial
Reliability
Reliable
Target: Ai2 playground web application (version not specified)
No auth needed
Prerequisites: Access to the target web application · Knowledge of the message ID format
devstral-2 · analyzed Feb 18, 2026 Full analysis →

References (1)

Core 1
Core References

Scores

CVSS v3 8.8
EPSS 0.0035
EPSS Percentile 26.8%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment
Exploitation poc
Automatable no
Technical Impact total

Details

CWE
CWE-639
Status published
Published Jul 22, 2025
Tracked Since Feb 18, 2026