Friday 26 June 2026 18:49:01 GMT+02:00

Netcrook

HomeManifesto
News
Techcrook
Geocrook
WikicrookTeamAppContact
EnglishItalianoArabic

#AI gateway


LiteLLM’s Host Header Slip Turns an AI Gateway Into a Trust Problem

Published: 17 June 2026 08:30Category: Vulnerabilities & Patch ManagementGeo: North America / USAAuthor: DEEPAUDIT

A critical authentication bypass in a widely used LLM proxy shows how a classic web flaw can become far more serious when it hits the control plane.

When the AI Gateway Becomes the Prize

Published: 16 June 2026 13:02Category: Vulnerabilities & Patch ManagementGeo: North America / USAAuthor: NEONPALADIN

A reported LiteLLM flaw chain shows how a proxy that concentrates access, secrets, and admin power can turn a low-privilege account into a gateway-level security event.

AI Proxy Bugs Can Turn a Preview Button Into a Server Shell

Published: 09 June 2026 17:19Category: Vulnerabilities & Patch ManagementGeo: North America / USAAuthor: SECURESPECTER

A LiteLLM vulnerability chain underscores how one command-injection path and one Host-header trust flaw can collide into a high-risk control-plane exposure.

When a Preview Button Turns into a Shell

Published: 09 June 2026 10:39Category: Vulnerabilities & Patch ManagementGeo: North America / USAAuthor: SECURESPECTER

A high-severity LiteLLM command-injection bug shows how AI gateway control panels can collapse into host-level risk when role checks are too loose.

The AI Gateway Becomes the Prize in Enterprise Security

Published: 02 June 2026 02:16Category: AI Security & Agentic SystemsGeo: North America / USAAuthor: KERNELWATCHER

Palo Alto Networks’ Portkey acquisition shows how control over prompts, routing, and agent behavior is turning into the new security battleground.

LiteLLM Turns Into a Trust Trap in an AI Supply-Chain Theft Case

Published: 27 May 2026 18:28Category: CybercrimeGeo: North America / USAAuthor: CRYSTALPROXY

A reported campaign tied to TeamPCP shows how a single AI middleware package can become a high-value path to secrets, even when the exact compromise method remains unclear.

Four Flaws, One Control Plane: Why OpenClaw’s Chained Risk Matters

Published: 16 May 2026 00:09Category: Vulnerabilities & Patch ManagementAuthor: NEONPALADIN

A newly disclosed chain of OpenClaw weaknesses shows how layered bugs in an AI gateway can turn a narrow opening into data exposure, elevated privileges, and long-lived access.

Pwn2Own Berlin Turns Browsers, Windows, and AI Gateways into Live Fire

Published: 15 May 2026 19:35Category: Research, Exploits & Offensive SecurityGeo: North America / USAAuthor: DEBUGSAGE

A sanctioned exploit contest put Microsoft Edge, Windows 11, LiteLLM, and NVIDIA-related technologies under pressure, showing how today’s attack surface reaches from the browser sandbox to AI control planes.

Pwn2Own’s Berlin Shockwave: Browsers, Windows, and AI Gateways All Took Hits in One Day

Published: 15 May 2026 12:17Category: Research, Exploits & Offensive SecurityGeo: North America / USAAuthor: DEBUGSAGE

A controlled exploit contest in Berlin turned into a stress test for modern security layers, with researchers demonstrating 24 unique zero-days across Microsoft Edge, Windows 11, LiteLLM, and NVIDIA-related targets.