LiteLLM
Open-source gateway that gives applications and agents one API in front of many model providers, with key management and routing.
Open-source gateway that gives applications and agents one API in front of many model providers, with key management and routing.
Security and assurance angle
It sits on the credential path for agent traffic; at Pwn2Own Ireland day one (Oct 6 2026) Taisic Yun (Xint) chained input validation and code injection into a reverse shell for a $40,000 award, and Out of Bounds earned $15,000 with four bugs, two of them already known (ZDI; Infosecurity Magazine). No CVE published yet. Oct 9 2026 final results: Pwn2Own Ireland paid $1.2M+ in total, with $40,000 awards also for OpenAI Codex, Nvidia Dynamo and Oracle Autonomous AI Database (SecurityWeek). Separately, Lumen’s Black Lotus Labs says PoeLLM cryptojacking malware has infected 3,000+ servers since April 2026, mostly internet-facing LiteLLM and Ollama instances (The Register, Oct 7 2026). On Nov 18 2026 CISA added CVE-2026-40217, a sandbox escape in the custom-code guardrail test endpoint disclosed in May, to its Known Exploited Vulnerabilities catalog (LiteLLM guardrail sandbox escape (CVE-2026-40217)).
Timeline
Every dated event in the wiki that involves LiteLLM, newest first.
- CISA lists a LiteLLM guardrail sandbox escape (CVE-2026-40217) as exploited (LiteLLM guardrail sandbox escape (CVE-2026-40217))
CISA added the flaw in the open-source LLM gateway to its Known Exploited Vulnerabilities catalog on Nov 18 with a Dec 2 deadline. Per the May 2026 GitHub advisory, the custom-code guardrail test endpoint ran user-supplied Python in a hand-rolled sandbox that could be escaped for code execution in the proxy process, which runs as root in the default Docker image; it needs a proxy-admin credential by default. Versions 1.81.8 to before 1.83.10 are affected. CISA did not say who exploited it, and no source we found says AI was used.
- Amazon decoys capture ARTEX agents running AI-key theft and deepfake KYC campaigns (ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026))
Amazon Threat Intelligence says its MadPot sensors, posing as LLM inference APIs, received requests from ARTEX agents carrying their own campaign memory between Oct 3 and Nov 5. The records describe Chinese-nexus groups (moderate confidence) stealing AI provider keys from exposed gateways and app builders such as LiteLLM, Langflow and RAGFlow, with stolen keys funding further hunting, and a separate attempt to beat crypto-exchange KYC checks with real-time deepfakes, which the vendor's server rejected in every recorded attempt.
Sources: AWS Security Blog, “Amazon Threat Intelligence observes threat actors running cybercrime campaigns with ARTEX AI agents”
Malware hijacked 3,000+ internet-facing LiteLLM and Ollama servers to mine cryptocurrency, hiding its command server in a poem.
Sources: Help Net Security, “Cryptomining botnet hides C2 addresses in GitHub poem, infects over 3,400 servers” (citing Lumen Black Lotus Labs)
- Pwn2Own Ireland: AI tools exploited
Codex and LiteLLM fall on day one ($40,000 each); final results include Nvidia Dynamo.
Sources: Cybersecurity News; SecurityWeek, “Google Pixel 10 Exploits Earned Hackers $560,000 at Pwn2Own”
Connections
LiteLLM and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →
What links here
Incident ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026) · LiteLLM guardrail sandbox escape (CVE-2026-40217) · PoeLLM cryptojacking
Concept Inference
Product Ollama
Sources
- Infosecurity Magazine, “Pwn2Own Hackers Find 32 Zero-Day Vulnerabilities on Day One”, Oct 7 2026
- ZDI, “Pwn2Own Ireland 2026 - Day One Results”, Oct 6 2026
- SecurityWeek, “Google Pixel 10 Exploits Earned Hackers $560,000 at Pwn2Own”, Oct 9 2026
- The Register, “Poetry is the new AI security threat as PoeLLM malware infects 3K+ servers”, Oct 7 2026
- GitHub, “Sandbox escape in custom-code guardrail (GHSA-wxxx-gvqv-xp7p)”, May 7 2026