LiteLLM CVE-2026-40217 Is Exploited From Virtual Keys. How to Check Your Proxy LiteLLM proxy versions 1.81.8 through 1.83.10 contain a sandbox-escape vulnerability, CVE-2026-40217, that lets attackers escalate virtual inference keys to administrative credentials and then execute code as root in the default Docker image. CISA added the flaw to its Known Exploited Vulnerabilities catalog on November 18, 2026, with a December 2 remediation deadline for federal agencies, after Google's Threat Intelligence Group reported in-the-wild exploitation. The fix, which replaces the regex deny-list with RestrictedPython, was merged in April and shipped in 1.83.10 per the advisory metadata (1.83.11 per the advisory text), with the full privilege-escalation chain closed in v1.83.14-stable. If you run a LiteLLM proxy, the box sitting in front of your OpenAI, Anthropic and Gemini accounts has a code execution bug that attackers are using right now. CISA added LiteLLM CVE-2026-40217 to its Known Exploited Vulnerabilities catalog on November 18, 2026, with a December 2 deadline for federal agencies Mallory summary of the KEV addition https://mallory.ai/stories/01a1f125-fa0c-7bc8-8018-acabeaaacd03 . Google says it watched a threat actor use it to turn ordinary virtual keys into admin credentials. The fix was merged on April 15. If your proxy hasn't been upgraded since spring, here is how to check the version, what to upgrade to it isn't the version the advisory names , which logs to grep and which keys to rotate. LiteLLM lets you write custom guardrails in Python. To test one, the proxy exposes POST /guardrails/test custom code , which runs whatever code you send it inside a hand-rolled sandbox. That sandbox was a regex deny-list over the source text. X41 D-Sec showed you could build the blocked names at runtime so the regex never sees them, then rewrite a generator's bytecode to reach the real import machinery and run OS commands X41 advisory https://www.x41-dsec.de/lab/advisories/x41-2026-001-litellm . In the default Docker image the proxy runs as root, so "code execution in the proxy process" means root in the container. The facts, from the GitHub advisory GHSA-wxxx-gvqv-xp7p https://github.com/advisories/GHSA-wxxx-gvqv-xp7p : | Affected | litellm = 1.81.8, < 1.83.10 the endpoint first shipped in 1.81.8 | | Fixed | 1.83.10 in the advisory metadata, 1.83.11 in the advisory text | | CVSS | 8.8 v3.1, Red Hat https://access.redhat.com/security/cve/cve-2026-40217 ; 7.5 High v4.0, GHSA | | CWE | CWE-420 Unprotected Alternate Channel, CWE-913 | | EPSS | 17.02% 97th percentile, per GHSA | The fix replaced the regex filter with RestrictedPython. That's the argument I keep seeing for putting this one off. The advisory does say reaching the endpoint takes a proxy-admin credential. In practice that requirement is weaker than it sounds, for two reasons. First, Obsidian Security published a chain in June that starts from a default internal user Obsidian write-up https://www.obsidiansecurity.com/blog/litellm-privilege-escalation-rce . CVE-2026-47101: /key/generate and /key/update , /key/regenerate stored a caller-supplied allowed routes without validating it, so a non-admin could mint a key that reaches admin routes. CVE-2026-47102: /user/update let you set your own user role to proxy admin . CVE-2026-40217 is the last step, from admin to shell. The full chain was closed in v1.83.14-stable, released April 25. Second, the in-the-wild exploitation matches that pattern. Google's Threat Intelligence Group wrote on November 17 that they "observed a threat actor exploit CVE-2026-40217, a sandbox escape in LiteLLM that allows an attacker to elevate limited-access inference keys "Virtual Keys" into full administrative credentials" GTIG AI Threat Tracker https://cloud.google.com/blog/topics/threat-intelligence/agentic-threat-activity-crosses-a-significant-threshold . The same report notes that in the intrusions it covers, privileged service accounts were enough for persistence and the attackers didn't need malware at all. So a virtual key, the kind you hand to every internal app and every intern's notebook, became the keys to the gateway. Those keys end up in .env files, CI logs and Slack. Whatever "PR:H" says, a credential that widely shared is not a high bar. What attackers do with that access is LLMjacking. The same GTIG report cites Mandiant incidents from 2026 where "single-day fraudulent charges exceeded $100,000 USD" and, in the worst cases, "cumulative resource abuse reached $1 million USD before remediation." pip show litellm | grep -i '^version' docker ps --format '{{.Names}}\t{{.Image}}' | grep -i litellm docker exec