LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters
CVE-2026-84377 · GHSA-3cv6-jpf6-8222 · published 2026-09-30
- Severity
- Medium
- CVSS score
- 6.5
- Chance of exploitation (EPSS)
- 0.54%
- Fixed in
- 1.96.2
- Exploitation No known exploitation
- Automatable No
- Technical impact Partial
- CISA SSVC
Any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination they control and cause the proxy to send its own configured provider credentials to that destination. The proxy's request-body validation was a denylist that did not cover every sensitive parameter and did not inspect parameters nested inside other request fields, so a caller could supply a routing or credential value that the proxy applied without clearing the operator's stored key. Any authenticated user could therefore exfiltrate the operator's upstream provider credentials and other configured secrets, and perform Server-Side Request Forgery against internal services reachable from the proxy.
Upgrade litellm to 1.96.2 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Fixed in 1.96.2, 1.95.1, 1.94.3, 1.93.2, 1.92.2, 1.91.5, 1.90.7, 1.89.7, and 1.88.6.
Set general_settings.allow_client_side_credentials to false so callers cannot override connection parameters, restrict proxy keys to trusted callers, and block the affected parameters (api_base, base_url, model_list, fallbacks, provider credential fields) at a reverse proxy or API gateway.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| litellm | PyPI | < 1.88.6 | 1.88.6 |
| litellm | PyPI | >= 1.89.0, < 1.89.7 | 1.89.7 |
| litellm | PyPI | >= 1.90.0, < 1.90.7 | 1.90.7 |
| litellm | PyPI | >= 1.91.0, < 1.91.5 | 1.91.5 |
| litellm | PyPI | >= 1.92.0, < 1.92.2 | 1.92.2 |
| litellm | PyPI | >= 1.93.0, < 1.93.2 | 1.93.2 |
| litellm | PyPI | >= 1.94.0, < 1.94.3 | 1.94.3 |
| litellm | PyPI | >= 1.95.0, < 1.95.1 | 1.95.1 |
| litellm | PyPI | >= 1.96.0, < 1.96.2 | 1.96.2 |
2 registered MCP servers install an affected version today, by the dependency versions a fresh install resolves.
- io.github.airas-org/airaslitellm@1.84.0
- io.github.Brightdotdev/darwin-raglitellm@1.83.14
- CriticalMLflow: Unauthenticated full-read SSRF in webhook delivery: _validate_webhook_url bypassed via unvalidated HTTP redirects (and DNS rebindingmlflowExploited
- Critical@zereight/mcp-gitlab Vulnerable to Server-Side Request Forgery@zereight/mcp-gitlab
- CriticalSSRF + LLM API key exfiltration via user-controlled basepath / baseUrl in 8 chat-model nodesflowise, flowise-components
- CriticalLocalAI POST /models/apply permits unauthenticated server-side request forgery through gallery URLsgithub.com/mudler/LocalAI
- CriticalFastMCP OpenAPI Provider has an SSRF & Path Traversal Vulnerabilityfastmcp
- CriticalBentoML SSRF Vulnerability in File Upload Processingbentoml
- 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.