Affected versions
- Affected versions
- >= 1.1.0-M1, < 1.1.6
- Fixed version
- 1.1.6
- Affected versions
- < 1.0.7
- Fixed version
- 1.0.7
Exploitation
Description
A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns.

