BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints
CVE-2026-12797 · GHSA-p897-vf7j-f5h8 · published 2026-06-21 · updated 2026-09-14
- Severity
- Low
- CVSS score
- 6.3
- Chance of exploitation (EPSS)
- 0.40%
- Fixed in
- No fix yet
- Exploitation Public proof of concept
- Automatable No
- Technical impact Partial
- CISA SSVC
A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure.
No fixed release is listed yet for litellm. Limit what it can reach, or stop using it until a fix ships, and follow the source advisory for updates.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| litellm | PyPI | <= 1.82.5 | No fix yet |
- CriticalMarimo: Pre-Auth Remote Code Execution via Terminal WebSocket Authentication BypassmarimoExploited
- CriticalLangflow CORS misconfiguration enables Account Takeover and RCElangflowExploited
- HighLangflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's FlowlangflowExploited
- CriticalTodoist MCP Server: Browser DNS rebinding lets websites write and delete Todoist data through local MCP server@doist/todoist-mcp
- CriticalLangflow: Unauthenticated Flow Execution via Webhook Authentication Bypasslangflow
- Critical[mcp-atlassian] Authentication bypass in HTTP transport: AtlassianOpaqueTokenVerifier accepts any non-empty tokenmcp-atlassian
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbacklitellmExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalLiteLLM vulnerable to server-side template injection in the /prompts/test endpointlitellm
- CriticalMalicious code in litellm (PyPI)litellm, litellm, litellm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.