Answer in brief
CVE-2026-59822 records a High severity (CVSS 8.8) vulnerability in LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback. The current sources mark it as known exploited. The current feed maps BerriAI/litellm (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.8. Known-exploitation status makes exposure review time-sensitive. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps BerriAI/litellm (generic). Check affected ranges and fixed versions before updating.
| Product | Affected versions | Fixed versions |
|---|---|---|
| cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* | Not reported | Not reported |
| Package | Affected range | Fixed version |
|---|---|---|
| BerriAI/litellmgeneric | < 1.84.0 | Not reported |
Published upstream
Jul 8, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 16, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jul 8, 2026
Added to CISA KEV
Sep 2, 2026
Evidence: source:kev:kev:kev:recordLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.
Quoted source text, attributed separately from HOL analysis.