| عنوان | paul-gauthier aider 0.86.3 Code Injection |
|---|
| الوصف | A prompt injection vulnerability exists in Aider v0.86.3 architect mode. The architect model's output is passed directly to the editor model via editor_coder.run(with_message=content, preproc=False), bypassing the normal preproc_user_input() layer that processes slash commands, file mentions, and URL preprocessing. This allows an attacker to embed a malicious instruction (e.g., "ARCHITECT OVERRIDE") inside repository content such as README.md. When the architect mode reads this poisoned file, the architect model emits attacker‑controlled code, which the editor model then applies to source files without further validation. In a verified attack, the editor injected a backdoor into auth.py that read the local .env file, base64‑encoded its contents, and sent them to an attacker‑controlled endpoint, after which Aider committed the backdoored file automatically. The vulnerability results in remote code execution and sensitive data exfiltration. |
|---|
| المصدر | ⚠️ https://github.com/Aider-AI/aider/issues/5058 |
|---|
| المستخدم | tchen200311 (UID 97733) |
|---|
| ارسال | 06/05/2026 02:38 AM (30 أيام منذ) |
|---|
| الاعتدال | 30/05/2026 06:21 PM (25 days later) |
|---|
| الحالة | تمت الموافقة |
|---|
| إدخال VulDB | 367456 [Aider-AI Aider 0.86.3 Architect Mode auth.py editor_coder.run تجاوز الصلاحيات] |
|---|
| النقاط | 20 |
|---|