---
title: "CISA puts the AI gateway LiteLLM on its exploited-flaws list; federal agencies patch by December 2"
description: "A flaw in the free AI gateway LiteLLM is now on CISA's exploited list, and the credential it demands is the same one AI attackers have been caught harvesting from gateways just like it. The spending this pushes toward managed, accountable plumbing is what moves, and Cloudflare sits in that seat."
publisher: "The Inference"
section: "Security"
published: 2026-11-19T15:44:15.767Z
modified: 2026-11-19T15:44:15.767Z
canonical: https://theinference.org/article/cisa-puts-the-ai-gateway-litellm-on-its-exploited-flaws-list-federal-agencies-patch-by-december-2
language: en
keywords: "Security, CISA, Cloudflare, Vulnerabilities, AI Agents"
---

# CISA puts the AI gateway LiteLLM on its exploited-flaws list; federal agencies patch by December 2

> A flaw in the free AI gateway LiteLLM is now on CISA's exploited list, and the credential it demands is the same one AI attackers have been caught harvesting from gateways just like it. The spending this pushes toward managed, accountable plumbing is what moves, and Cloudflare sits in that seat.

CISA put a flaw in [LiteLLM](https://theinference.org/markets/companies/litellm) [on its Known Exploited Vulnerabilities catalog](https://www.cisa.gov/news-events/alerts/2026/11/18/cisa-adds-four-known-exploited-vulnerabilities-catalog) on November 18, 2026, which means the agency holds evidence that attackers are already using it [1][2]. LiteLLM is the free, open-source gateway teams park between their coding agents and [OpenAI](https://theinference.org/markets/companies/openai), [Anthropic](https://theinference.org/markets/companies/anthropic) or Google; one install holds every provider key, budget and guardrail in the stack [3][4]. The story was never really the bug. It is the admin credential the bug needs, and that credential is exactly what [a separate campaign of AI attackers has been caught harvesting](https://theinference.org/article/amazon-decoy-servers-catch-ai-agents-stealing-api-keys-fbi-clocks-some-intrusions-at-under-three-hours) [5][6].

## The escape lands in a process that holds every key

The flaw, CVE-2026-40217, sits on a route for testing custom guardrail code [6]. The project's own [advisory of May 7, 2026](https://github.com/BerriAI/litellm/security/advisories/GHSA-wxxx-gvqv-xp7p), is blunt: the hand-rolled sandbox around that route could be escaped with bytecode techniques, giving code execution in the proxy process, which runs as root in the default Docker image [6]. [Reporting on the original disclosure](https://shattered.io/litellm-axis-redcap-synology-dsm-four-flaws-join-cisa-kev-nov-18/) says the sandbox blocked dangerous names like __import__ by scanning source text with regular expressions, and an attacker simply assembles those names at runtime instead [3]. The catch is access: reaching the route requires the proxy's master key [6].

## The key it needs is the key the agents are stealing

[Amazon's threat-intelligence decoys, posing as model services, captured the working records of AI agents](https://thehackernews.com/2026/11/amazon-uncovers-ai-agent-campaign.html) running a playbook of weak entry points, LiteLLM's default master key among them, and the stolen keys were used to run the very models that powered the hunt for more [5]. [Microsoft](https://theinference.org/markets/companies/microsoft) separately described a LiteLLM gateway compromise that exposed provider keys on August 26 [5]. [Amazon](https://theinference.org/markets/companies/amazon) assesses, with moderate confidence, that the agents ran on ARTEX, an open-source penetration-testing tool the FBI says many kinds of attackers have used since at least August [5]. A default master key left in place turns a credentials footnote into code execution.

## Two weeks for the keyed flaw, three days for the rest

[CISA's deadlines price the same gate](https://theinference.org/article/cisa-orders-federal-agencies-to-patch-check-point-s-exploited-root-access-flaw-by-monday). Federal agencies have until December 2 for LiteLLM, while the batch's other three flaws, none of which require a login, are due November 21; only the LiteLLM entry is marked as needing no forensic triage [2]. Scores disagree, GitHub calling the flaw moderate while the federal database scores it 8.8, and the listing settles the question, because exploitation is a fact about attackers rather than a severity model [3][6][7]. [Private teams should still hunt](https://theinference.org/article/1-000-exposed-gitlab-servers-later-the-patch-clock-belongs-to-a-partner): a fix does not evict an intruder, and it does not rotate the provider keys behind the proxy [5][9].

*Chart: **The keyed AI-gateway flaw gets two weeks; the no-login flaws get three days** Bar chart of days from listing to federal remediation deadline for the four flaws CISA added to its KEV catalog on November 18, 2026: LiteLLM 14 days, Synology DSM, REDCap and Apache Axis 3 days each.*

*Days from CISA's November 18, 2026 KEV listing to the federal remediation due date under BOD 26-04. Source: CISA Known Exploited Vulnerabilities catalog, November 18, 2026. [2]*

## The spend follows whoever is accountable for it

BerriAI, LiteLLM's maker, already sells the accountable version, an enterprise tier with single sign-on and audit logs over the same open core, plus a managed cloud in beta, on a base the project says has passed 500 million Docker pulls [4]. Reporting says Red Hat bundles the gateway inside Ansible Automation Platform and OpenShift AI, with fixes of its own [3].

The listed name further up the stack is [Cloudflare](https://theinference.org/markets/companies/cloudflare) (NYSE: NET), whose finance chief Thomas Seifert [said on November 18 that machine traffic is about 68% of its network](https://finance.yahoo.com/technology/ai/articles/cloudflare-cfo-sees-ai-security-191250041.html), that Cloudflare has begun monetizing products that let agents transact and identify themselves, and that security concerns are shortening some sales cycles [8]. Urgency about AI plumbing is already moving budgets, and the projection is where that spend lands.

## The bottleneck is ownership, not the model

None of this argues against the agent stack; it argues for running it like production. Teams on LiteLLM should be at 1.83.11 or later today, rotate the master key and every provider key behind it, and block the test route at the edge until the upgrade lands [6]. LiteLLM shipped the fix that same week in May. What has been missing since is anyone accountable for applying it.

## Takeaway

The LiteLLM flaw needs the proxy's master key, and that same credential is what AI agents have been caught harvesting from default installs, which is why the money moves toward gateways someone is accountable for.

## Sources

1. [CISA, "CISA Adds Four Known Exploited Vulnerabilities to Catalog," 18 November 2026](https://www.cisa.gov/news-events/alerts/2026/11/18/cisa-adds-four-known-exploited-vulnerabilities-catalog)
2. [CISA, Known Exploited Vulnerabilities Catalog, JSON feed, version 2026.11.18, 18 November 2026](https://www.cisa.gov/sites/default/files/feeds/known_exploited_vulnerabilities.json)
3. [Shattered.io, "LiteLLM, Axis, REDCap, DSM: 4 Flaws Join CISA KEV," 19 November 2026](https://shattered.io/litellm-axis-redcap-synology-dsm-four-flaws-join-cisa-kev-nov-18/)
4. [LiteLLM (BerriAI), product homepage, accessed 19 November 2026](https://www.litellm.ai/)
5. [The Hacker News, "Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API Keys," 16 November 2026](https://thehackernews.com/2026/11/amazon-uncovers-ai-agent-campaign.html)
6. [GitHub, BerriAI/litellm advisory GHSA-wxxx-gvqv-xp7p, "Sandbox escape in custom-code guardrail," 7 May 2026](https://github.com/BerriAI/litellm/security/advisories/GHSA-wxxx-gvqv-xp7p)
7. [heise online, "Angriffe auf Lücken in Apache Axis und Roller, LiteLLM, Synology und mehr," November 2026](https://www.heise.de/news/Angriffe-auf-Luecken-in-Apache-Axis-und-Roller-LiteLLM-Synology-und-mehr-11530429.html)
8. [MarketBeat via Yahoo Finance, "Cloudflare CFO Sees AI and Security Demand Surge, But Warns Against Another Big Beat," 18 November 2026](https://finance.yahoo.com/technology/ai/articles/cloudflare-cfo-sees-ai-security-191250041.html)
9. [The Agentic Times, "CISA flags exploited LiteLLM flaw in US federal patch catalogue," 19 November 2026](https://theagentictimes.org/vulnerabilities/cisa-flags-exploited-litellm-flaw-in-us-federal-patch-catalogue)


---

CISA puts the AI gateway LiteLLM on its exploited-flaws list; federal agencies patch by December 2 — The Inference. Canonical: https://theinference.org/article/cisa-puts-the-ai-gateway-litellm-on-its-exploited-flaws-list-federal-agencies-patch-by-december-2
