目标达成 感谢每一位支持者 — 我们达成了 100% 目标!

目标: 1000 元 · 已筹: 1336

100%

CVE-2025-51867 PoC — Deepfiction AI 安全漏洞

来源
关联漏洞
标题: Deepfiction AI 安全漏洞 (CVE-2025-51867)
Description:Deepfiction AI是Deepfiction AI公司的一个人工智能平台。 Deepfiction AI 2025-06-03及之前版本存在安全漏洞,该漏洞源于不安全的直接对象引用,可能导致使用其他用户积分与LLM聊天。
介绍
# CVE-2025-51867
## Vulnerability description

   Deepfiction AI is an AI entertainment company with a mission to revolutionize personalized storytelling. Deepfiction AI provide a web application to create stories by chatting with LLM, which is vulnerable to Insecure Direct Object Reference (IDOR) in its chat component. An attacker can exploit this IDOR to chat with LLM with other users' credits.

## Attack Vectors

   The API endpoint `https://www.deepfiction.ai/api/story/create-story-part` is utilized to initiate or continue conversations. Testing indicates that this API solely relies on the `treatment_id` and `user_id` fields within the request body for access control.

   It has been observed that `id` and `author_id` fields are exposed in publicly accessible conversations listed on the webpage `https://www.deepfiction.ai/browse/stories`. These exposed fields directly correspond to the `treatment_id` (mapping to `id`) and `user_id` (mapping to `author_id`) parameters expected by the `create-story-part` API.

   As a result, an attacker can substitute the leaked `id` (as `treatment_id`) and `author_id` (as `user_id`) into requests to this API. This enables them to interact with the Large Language Model (LLM) by consuming the credits of other users. The figures shows the POC of this vulnerability.

   ![Figure 1 IDOR](./figure1.png)

   ![Figure 2 id leakage](./figure2.png)

   Additionally, analysis of network traffic (e.g., through packet capture) can reveal the specific role configurations (character settings) for each Character. These configurations are analogous to system prompts and represent important system resources of the LLM ChatBot. This exposure also constitutes a form of sensitive data leakage, as it may reveal proprietary prompt engineering details or character definitions.

   ![Figure 3 role configuration leakage](./figure3.png)

## Vulnerability affected

   This vulnerability can have an impact on any user of https://www.deepfiction.ai. The chat credit of user will be abused with leaked treatment_id and user_id.
文件快照

登录后查看神龙缓存的 POC 文件快照

登录查看
备注
    1. 建议优先通过来源进行访问。
    2. 本地 POC 快照面向订阅用户开放;当原始来源失效或无法访问时,本地镜像作为订阅权益的一部分提供。
    3. 持续抓取、验证、维护这份 POC 档案需要不少投入,因此本地快照已纳入付费订阅。您的订阅是让这份资料能继续走下去的关键,由衷感谢。 查看订阅方案 →