llm security

AI Security Incident Case: Account Takeover Due to Meta AI Support Assistant Authorization Flaw

AI Security Incident Case: Account Takeover Due to Meta AI Support Assistant Authorization Flaw

| | AI agent, AI assistant, AI Risk, AI Security, Blog, llm security, Meta
Overview Between late May and early June 2026, several high-profile Instagram accounts were reportedly taken over by attackers, including Barack Obama’s White House account, the personal account of U.S. Space Force Chief ...
NSFOCUS
AI Security Incident Case: Both Grok and Gemini Hallucinated When Verifying Minab Cemetery Photo

AI Security Incident Case: Both Grok and Gemini Hallucinated When Verifying Minab Cemetery Photo

| | AI hallucination, AI Security, Blog, llm security
Overview A core risk within AI security threats lies in the reliability of AI models, manifested as distorted outputs, hallucinations, and the generation of misleading content. While these issues may seem like ...
NSFOCUS

Bypassing LLM Supervisor Agents Through Indirect Prompt Injection

| | AI agent security, AI Security, LLM penetration testing, LLM Red Teaming, llm security, Offensive Security, prompt injection
Indirect prompt injection lets attackers bypass LLM supervisor agents by hiding malicious instructions in profile fields and contextual data. Learn how this attack works and how to defend against it. The post ...
Offensive Security Blog: Latest Trends in Hacking | Praetorian
AI Infrastructure LiteLLM Supply Chain Poisoning Alert

AI Infrastructure LiteLLM Supply Chain Poisoning Alert

| | AI Risk, AI Security, Blog, Emergency Response, LiteLLM, llm security, supply chain attack, TeamPCP
Overview Recently, NSFOCUS Technology CERT detected that the GitHub community disclosed that there was a credential stealing program in the new version of LiteLLM. Analysis confirmed that it had suffered supply chain ...
NSFOCUS, Inc., a global network and cyber security leader, protects enterprises and carriers from advanced cyber attacks.

Novee Brings Autonomous Red Teaming to LLM Applications, Built From Its Own Vulnerability Research

| | Agentic AI, AI Red Teaming, AI Security, llm security, Penetration Testing, RSAC 2026
Novee has introduced AI Red Teaming for LLM Applications, an autonomous security testing capability built into its AI penetration testing platform. The product is designed to find vulnerabilities in AI-powered applications before ...

Julius v0.2.0: From 33 to 63 Probes — Now Detecting Cloud AI, Enterprise Inference, and RAG Pipelines

| | AI infrastructure, AI Offensive Security, Cloud AI, Julius, llm security, Offensive Security, open source, Open Source Tools, RAG security
TL;DR: Julius v0.2.0 nearly doubles LLM fingerprinting probe coverage from 33 to 63, adding detection for cloud-managed AI services (AWS Bedrock, Azure OpenAI, Vertex AI), high-performance inference servers (SGLang, TensorRT-LLM, Triton), AI ...
Offensive Security Blog: Latest Trends in Hacking | Praetorian
Insights into Claude Code Security: A New Pattern of Intelligent Attack and Defense

Insights into Claude Code Security: A New Pattern of Intelligent Attack and Defense

| | AI, AI Security, AI Tools, Anthropic, Blog, Claude Code Security, code audit, Frontier Red Team, LLM, llm security, NSFGPT AI security capability platform, NSFGPT;, NSFOCUS AI Automated Penetration Testing, SAST
On February 20, 2026, AI company Anthropic released a new code security tool called Claude Code Security. This release coincided with the highly sensitive period of global capital markets to AI technology ...
NSFOCUS, Inc., a global network and cyber security leader, protects enterprises and carriers from advanced cyber attacks.
SOC Engineers Go Deep on AI SOC Guardrails

SOC Engineers Go Deep on AI SOC Guardrails

| | AI guardrails, AI-SOC, Autonomous SOC, llm security, Security Automation, security orchestration
What to automate, what needs human approval, and why 'the AI did it' won't satisfy your auditors" would pull better. The post SOC Engineers Go Deep on AI SOC Guardrails appeared first ...
D3 Security
Analysis of the Attack Surface in the Agent SKILL Architecture: Case Studies and Ecosystem Research

Analysis of the Attack Surface in the Agent SKILL Architecture: Case Studies and Ecosystem Research

| | AI agent, AI Security, Blog, coding security, LLM, llm security, MCP, SKILL, Skills
Background As LLMs and intelligent agents expand from dialogue to task execution, the encapsulation, reuse and orchestration of LLM capabilities have become key issues. As a capability abstraction mechanism, SKILL encapsulates reasoning ...
NSFOCUS, Inc., a global network and cyber security leader, protects enterprises and carriers from advanced cyber attacks.
NSFOCUS Unveils Enhanced AI LLM Risk Threat Matrix for Holistic AI Security Governance

NSFOCUS Unveils Enhanced AI LLM Risk Threat Matrix for Holistic AI Security Governance

| | AI Security, AI-scan, Blog, LLM protection, LLM Risk, llm security, Press Releases
SANTA CLARA, Calif., Jan 29, 2026 – Security is a prerequisite for the application and development of LLM technology. Only by addressing security risks when integrating LLMs can businesses ensure healthy and sustainable ...
NSFOCUS, Inc., a global network and cyber security leader, protects enterprises and carriers from advanced cyber attacks.
Load more