Written by: Christopher Romano, Codi Starks, Garrett Mahoney, John Wolfram, Josh Murchie, K Singh, Mathew Potaczek, Mike Lombardi, Rik Dolfing Introduction Mandiant responded to multiple incidents in 2026 in which threat actors hijacked enterprise access to Large Language Models (LLMs), a tactic known as "LLMJacking." Spanning a variety of cloud and LLM providers, these intrusions impacted organizations in North America, South America, and Asia Pacific across the financial services, retail,…
A critical PHP flaw, leaked Linux kernel reports, a poisoned LiteLLM release, and more, all in seven days. Which threats called for immediate action, and which generated more noise than real danger?
For the latest discoveries in cyber research for the week of 26th October, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES Japanese cloud hosting provider Onamae Desktop Cloud has confirmed a cyberattack in which intruders compromised its infrastructure and installed malware on customer servers. More than 26,000 servers were potentially affected. The provider began shutting down customer environments on October 21 to contain the intrusion and prevent further…
LiteLLM, an open-source tool widely used by artificial intelligence developers, said a key accidentally exposed in May was behind a supply-chain attack that is believed to have hit tens of thousands of users last week.
In this article Attack overview Technical details Mitigation and protection guidance Indicators of compromise References Learn More On October 21, 2026, a compromised LiteLLM 1.107.0 release was published to the Python Package Index (PyPI) and distributed through official container images. The malicious package added files that Python could execute during normal interpreter initialization. An application did not need to import LiteLLM for the payload to run: starting Python in an affected…
Hackers compromised the LiteLLM project's PyPI package and published malicious Docker images with a payload that steals credentials, secrets, and environment variables. [...]
LiteLLM 1.107.0 contains an infostealer and RAT, and PyPI has quarantined the package. See if you’re affected, what it steals, and what to rotate. Category: Vulnerabilities & Threats
At 11:39 UTC on October 21, a malicious version (1.107.0) of the LiteLLM package was uploaded to PyPI. This version was quarantined on PyPI as of 13:20 UTC. According to ClickPy data, the malicious version received approximately 49,000 downloads.LiteLLM Docker containers on GH...
TL;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLLM version 1.83.9. The most significant issues stemmed from a missing authorization check on the /config/update endpoint, which allowed any authenticated user (including low-privileged accounts) to modify the proxy’s runtime configuration. This single flaw enabled arbitrary file…
In this article AI workloads are becoming high-value control pointsCase study 1: LiteLLM gateway compromiseCase study 2: RAGFlow compromiseCase study 3: Kestra compromiseMitigation and protection guidanceMITRE ATT&CK techniques observedReferencesLearn more AI is creating a new layer of enterprise infrastructure. Gateways, retrieval platforms, orchestration services, and containerized runtimes now sit between users, applications, data, and models. These systems concentrate credentials, data…
The vulnerability exists in LiteLLM’s authentication flow, where the Authorization: Bearer header is directly concatenated into a SQL query without proper parameterization. This flaw allows attackers to inject arbitrary SQL statements prior to authentication, enabling direct a...
TeamPCP orchestrated one of the most sophisticated multi-ecosystem supply chain campaigns publicly documented to date that cascaded through developer tooling and compromised LiteLLM, exposing how AI proxy services that concentrate API keys and cloud credentials become high-value collateral when supply chain attacks compromise upstream dependencies.
Malicious versions of the LiteLLM python package (1.82.7 and 1.82.8) were published on the morning of 24 March 2026. The compromised packages employed two different methods to deliver their payload. The packages were published at approximately 8:30 UTC and quarantined by PyPI ...