GHSA-p897-vf7j-f5h8: BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints

Summary

A flaw in BerriAI litellm up to 1.82.5 affects the async_pre_call_hook function in enterprise/enterprise_hooks/banned_keywords.py, part of the Completions Interface. Manipulating the prompt argument results in incorrect authorization, and the attack can be carried out remotely. A public exploit has been released, and the vendor was contacted early about the disclosure.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• litellmPyPILLM dependency since 2023-07-27 · 54 tracked dependents

Related items

• CriticalHermes Agent - PKCE Session Takeover via Redirect-URI Parser ConfusionSimilar attack · Tenable Research Advisories
• LowLost in the comments: Social context as a single‐pass jailbreak and defense on agentic platformsSimilar attack · OpenAlex (peer-reviewed AI security)
• MediumGHSA-hmq2-7hp6-7crh: Banks: User-controlled prompt input can be parsed as privileged chat messagesSimilar attack · GitHub Advisory Database
• HighGHSA-6wjp-v33h-5cvq: PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent invocation and instruction disclosureSimilar attack · GitHub Advisory Database
• HighCVE-2026-101998: Docker Sandboxes fail open when masking credentials in proxy responsesSimilar attack · NVD/CVE Database