This vulnerability affects BerriAI litellm up to version 1.82.5 in the async_pre_call_hook function of enterprise/enterprise_hooks/banned_keywords.py. The issue arises from improper authorization checks when handling the prompt argument, enabling remote attackers to exploit this flaw. The vulnerability has been publicly disclosed and the exploit code is available, but no official fix or patch has been released by the vendor as of the publication date. The CVSS 4.0 vector indicates network attack vector, low attack complexity, no privileges required, no user interaction, and low to low impact on confidentiality, integrity, and availability.

The vulnerability allows remote attackers to bypass authorization controls by manipulating the prompt argument in the affected function. This could lead to unauthorized access or actions within the Completions Interface component of BerriAI litellm. The CVSS score of 5.3 reflects a medium impact with potential limited confidentiality, integrity, and availability consequences.

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or patch has been released, users should monitor vendor communications for updates. Until a patch is available, consider restricting access to the affected component and applying compensating controls to limit exposure to remote attacks.