CVE•Published 2026-07-08•Modified 2026-09-03•1 article on news•5 live references•NVD data
CVE-2026-59822Litellm · Litellm
Vulnerability data via NVD (ingested)
CVSS v3.1
8.2
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
EPSS percentile
42
Exploit Prediction Scoring System · top 58% of all CVEs
Description
LiteLLM 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.
Timeline
Published 2026-07-08
Modified 2026-09-03
External references
Search for exposed instances
Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).
Shodan · vuln tag0 hosts
vuln:CVE-2026-59822Hosts Shodan has explicitly fingerprinted as vulnerable.
Shodan · product
product:"Litellm Litellm"All exposed Litellm Litellm instances — cross-reference with the CVE's affected-version range.
Shodan · banner/body mention
http.html:"Litellm"HTTP body or banner mentions "Litellm" — catches deploys Shodan didn't identify as a product.
More intel sources (5)
Shodan report
vuln:CVE-2026-59822Country / ASN / product breakdown for the vuln query.
Censys
vulnerabilities.cve_id: CVE-2026-59822Censys host search filtered to this CVE id.
grep.app
CVE-2026-59822Public source-code mentions — fast PoC discovery.
GitHub code
CVE-2026-59822GitHub code search for direct mentions.
Google dork
"CVE-2026-59822" exploit -site:nvd.nist.govWrite-ups and news, NVD excluded.
Known PoCs on GitHub (7)
CVE-2026-598227 repos
Ostorlab/KEVunknown
Ostorlab KEV: One-command to detect most remotely known exploitable vulnerabilities. Sourced from CISA KEV, Google's Tsunami, Ostorlab's Asteroid and Bug Bounty programs.
webpro255/awesome-ai-agent-attacksunknown
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
anomixer/openclaw-newsJavaScript
OpenClaw Daily News (with Ollama + Telegram Quick Setup Guide) | 每日新聞兼快速安裝指南
mcp-security-project/mcp-cve-projectunknown
The Project shares all information on MCP related CVE's published
GODofExploit/exploit-arsenalPython
420 standalone Python-3 (stdlib-only) CVE exploits, each live-validated end-to-end against real vulnerable software with a write-up and a real-run screenshot. 102 in the CISA KEV c…
barmi/cve-patch-auditorGo
Audit CVE impact, patch status, remediation progress, and verification results across systems.
Aviral2642/ai-infra-securityPython
Vulnerability research on AI infrastructure: LLM gateways, MCP transports, and model-serving stacks. Root cause, reproduction, and detection.