Vigilbase CVEConnect your agent

BerriAI LiteLLM Improper Authentication Vulnerability

Exploited · KEV 2026-09-02CVE-2026-59822CWE-287CWE-306

Exploited since 2026-09-02. No WAF vendor names it yet.

Edge rules
0/8
Our test
No exploit yet
CVSS
8.8
EPSS
0.8% Top 42%
Posts, 14d
02026-10-21: 0 posts2026-10-22: 0 posts2026-10-23: 0 posts2026-10-24: 0 posts2026-10-25: 0 posts2026-10-26: 0 posts2026-10-27: 0 posts2026-10-28: 0 posts2026-10-29: 0 posts2026-10-30: 0 posts2026-10-31: 0 posts2026-11-01: 0 posts2026-11-02: 0 posts2026-11-03: 0 posts
Published
2026-07-08
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… More

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.

Ask Vigil

AI · answers from this page
Ask about CVE-2026-59822: who's covered, what to patch first, how vendors compare. I cite sources and won't help with attacks.

Workers AI (Llama 3.3). Can be wrong: check the cited source.

Severity, decoded

CVSS 4.0
High · 8.8 / 10

Exploitable over the network, with no privileges and no user interaction, leading to full loss of confidentiality and low impact on integrity.

Over the internetNo login neededNo user actionWorks reliablySerious impact
How the score is built11 metrics
  • Attack vectorAn attacker can reach it over the internet; no access to your network needed.
    Network
  • Attack complexityNo built-in defences have to be bypassed; the attack works reliably.
    Low
  • Attack requirementsThe attack works without any special deployment or timing conditions.
    None
  • Privileges requiredNo account or login is needed.
    None
  • User interactionNo one has to click or open anything; the attack works on its own.
    None
  • Confidentiality impact (vulnerable system)An attacker can read all data the affected component holds, or the most sensitive parts of it.
    High
  • Integrity impact (vulnerable system)An attacker can change some data, but with limited control or limited effect.
    Low
  • Availability impact (vulnerable system)The component keeps working normally.
    None
  • Confidentiality impact (other systems)Other systems' data is not exposed.
    None
  • Integrity impact (other systems)Other systems' data cannot be changed.
    None
  • Availability impact (other systems)Other systems keep working normally.
    None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N
CISA's assessmentSSVC, from the CVE record
ExploitationActive

Attackers are exploiting this in the wild.

AutomatableYes

Attackers can script the attack end to end and hit many targets at once.

Technical impactPartial

A successful attack gives limited control over the affected software or limited access to its data.

Public exploits

None found
0 Metasploit0 Exploit-DB0 Scanner template0 GitHub PoCs

No exploit in Exploit-DB or Metasploit, and no scanner template. That lowers, but doesn't remove, the chance of mass exploitation.

Timeline

  1. 2026-07-08
    CVE published
    CVE List
  2. 2026-09-02
    Added to CISA KEV
    Confirmed exploitation in the wild

Social

2026-10-21: 0 posts2026-10-22: 0 posts2026-10-23: 0 posts2026-10-24: 0 posts2026-10-25: 0 posts2026-10-26: 0 posts2026-10-27: 0 posts2026-10-28: 0 posts2026-10-29: 0 posts2026-10-30: 0 posts2026-10-31: 0 posts2026-11-01: 0 posts2026-11-02: 0 posts2026-11-03: 0 posts

No posts seen yet on X, Bluesky, Mastodon, Hacker News or GitHub.

Vendor statements

Quoted
CloudflareWAF Managed RulesNo public claim

We found no public statement from this vendor naming this CVE. That is not proof of no protection: generic rules may still catch it. Each row gives the rule ID and its default action. The feed starts in January 2025, so older rules are missing.

AWSAWS WAF Managed RulesNo public claim

We found no public statement from this vendor naming this CVE. That is not proof of no protection: generic rules may still catch it. AWS often describes a vulnerability without naming its CVE (for example "Log4j"). We count only entries that name the CVE, so AWS coverage is understated.

Microsoft AzureFront Door and Application Gateway WAF (DRS)No public claim

We found no public statement from this vendor naming this CVE. That is not proof of no protection: generic rules may still catch it. The rule tables name CVEs but carry no dates, so Azure is left out of every time-to-rule figure.

Google CloudCloud Armor preconfigured WAF rulesNo public claim

We found no public statement from this vendor naming this CVE. That is not proof of no protection: generic rules may still catch it. Google names few CVEs: the release notes start in May 2024 and the rules reference lists CVEs without dates. Its cve-canary rules are opt-in.

FastlyNext-Gen WAF virtual patchesBefore feed history

The CVE predates the oldest entry in this vendor's public feed, so a rule may exist that we cannot see.

F5Attack signatures (Distributed Cloud WAF)No public claim

We found no public statement from this vendor naming this CVE. That is not proof of no protection: generic rules may still catch it. Each signature lists the CVEs it references, with its id and date. F5 does not state a default action; signatures enforce once staging ends in your policy.

AkamaiApp & API Protector (Adaptive Security Engine)No public source

This vendor publishes no machine-readable rule changelog we can check.

OWASP CRSCore Rule Set (open source, used inside many WAFs)No public claim

We found no public statement from this vendor naming this CVE. That is not proof of no protection: generic rules may still catch it. CRS rarely names CVEs: it relies on generic detections. Our own lab measures what it actually blocks.