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.

Affected Spring Products and Versions

Spring AI:

• 1.0.0 - 1.0.x
• 1.1.0 - 1.1.x

Mitigation

Users of affected versions should upgrade to the corresponding fixed version.

Credit

The issue was reported responsibly by

• Ahmed Sekka (GitHub: https://github.com/ahmed-sekka)

References

• • https://nvd.nist.gov/vuln-metrics/cvss/v3-calculator?vector=AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N&version=3.1

History