Advisory record · GHSA-p897-vf7j-f5h8

BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints

CVSS 5.3 MediumEPSS 0.0040 · 34th percentile

Published by the GitHub Advisory Database at 21 Jun 2026, 12:30 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
litellmPyPI<=1.82.5No fixed version yet
Identifiers
GHSA-p897-vf7j-f5h8 · CVE-2026-12797 · PYSEC-2026-4074
Weakness (CWE)
CWE-285 · CWE-863
Published
21 Jun 2026
Updated
1 Oct 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

litellm versions up to and including 1.82.5 are affected by a security feature bypass in the BannedKeywords and AzureContentSafety guardrails on async endpoints, caused by a call_type mismatch. A remote attacker can manipulate the prompt to get past these guardrails, so content that should be blocked is not filtered. The source gives few details beyond this, and no fixed version is listed.

Written 1 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
5.3 Medium 4.0 CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P CNA (VulDB)
  • CISA KEV Not listed.
  • EPSS 0.0040, the 34th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:09 UTC First seen by agentprime
  2. 31 Oct 2026, 14:09 UTC Confirmed by OSV

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.