My local AI agent remembered things I never said. A reader's security review found it.
说明与用途
CORTEX 无意中存储了用户仅要求其处理的内容中的事实,导致内存错误。通过添加仅接受用户自述的过滤器并对事实进行根据信息验证,以及运行严格测试,问题已解决,内存现在仅保存用户提供的数据。
问题
CORTEX stored user facts from content the user only asked it to process, leading to unintended memory retention.
结果
All 13 memory cases passed after the fix; unit tests increased from 264 to 318, and memory now holds only user‑provided facts.
工作流
- 1. Identify user‑self statements via self_statements() and filter out quoted or fenced text.
- 2. Prevent the model from seeing the filtered material, so it cannot extract facts from unseen JSON.
- 3. Validate each extracted fact with _is_grounded() to ensure it appears in user words.
- 4. Run regression tests marked xfail to confirm the bug is fixed.
- 5. Merge PR and release v1.2.2.
- 6. Provide reset-memory command for users to clear unintended memory.
证据
Mustafa showed it was also storing facts from things I only asked it to process.
The last one is the nasty one. Remembered facts go into the system prompt, so a note pasted once would have shaped every later session.
13 memory cases × 3 runs on qwen2.5:7b: 24/39 before, 39/39 after.
The fix proves itself against his cases, not mine.
- 记录日期: 2026-10-02T12:55:49.986Z