Netcrook
#LiteLLM
When an AI Gateway Turns Into a Miner: The Quiet Theft of Cloud Compute
A compromised AWS-hosted AI gateway tied to Amazon Bedrock shows how generative AI middleware can become valuable enough to hijack for cryptocurrency mining.
LiteLLM’s Host Header Slip Turns an AI Gateway Into a Trust Problem
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.
One Header, Two Truths: How LiteLLM’s Auth Gate and Router Fell Out of Sync
A critical CVE in the AI proxy layer shows how a client-controlled Host header can split routing from authorization and turn a management plane into a soft target.
When the AI Gateway Becomes the Prize
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
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.
LiteLLM’s Hidden Test Paths Turned a Gateway Into a Command-Run Target
A chained flaw in an AI proxy gateway shows how preview and diagnostic endpoints can cross the line from convenience to host-level risk when they can launch subprocesses.
When a Preview Button Turns into a Shell
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.
LiteLLM Turns Into a Trust Trap in an AI Supply-Chain Theft Case
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.
Pwn2Own Berlin Turns Browsers, Windows, and AI Gateways into Live Fire
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
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.
LiteLLM’s Ghost Release Shows How Package Trust Can Fracture in Plain Sight
A PyPI version with no matching upstream trail turned a routine dependency check into a lesson in software provenance, release governance, and build-time trust.
Seconds to Zero-Day: Hackers Pounce on LiteLLM Flaw Before the Dust Settles
A critical SQL injection in LiteLLM was weaponized within hours, exposing API keys and credentials before most users could react.
Zero Day, Zero Delay: How Hackers Raided LiteLLM’s Vault in Just 36 Hours
A critical SQL injection flaw in the popular AI gateway LiteLLM was weaponized within hours, exposing cloud credentials and raising fresh alarms for open-source security.
Hackers Crack Open LiteLLM: How a Single Flaw Exposed the AI Gateway’s Secrets
A critical SQL injection bug in LiteLLM let attackers raid sensitive databases, exposing the backbone of countless AI apps.
Unseen Gateways: Hackers Breach AI Nerve Centers via LiteLLM SQL Injection Flaw
A critical vulnerability in LiteLLM exposes sensitive AI infrastructure, with attackers moving at record speed to steal secrets and credentials.
AI Gateways Under Siege: Sophisticated Hackers Exploit LiteLLM Flaw to Steal Critical Secrets
A newly discovered SQL injection vulnerability in LiteLLM exposes valuable API keys and credentials, escalating the threat to core AI infrastructure.
Shadow in the Supply Chain: Mercor Breach Reveals Open-Source Weakness
AI recruiter Mercor is among thousands caught in the LiteLLM supply chain attack, raising fresh alarms about the fragility of open-source software security.
Python’s Silent Sabotage: TeamPCP’s AI Supply Chain Attack Exposes Global Cloud Secrets
A sophisticated malware campaign poisons LiteLLM, risking millions of AI projects and cloud environments worldwide.
PyPI’s Poisoned Pill: LiteLLM Backdoor Breach Unleashes Credential Stealing Spree
A trusted AI developer tool is weaponized in a sweeping supply-chain attack, exposing secrets from hundreds of thousands of systems worldwide.
Supply Chain Dominoes: TeamPCP’s Relentless Sabotage of Python’s LiteLLM Shakes Developer Trust
A sophisticated backdoor campaign exploits software supply chains, exposing thousands of environments through cascading compromises.