NIST, CISA, NSA Guide Treats Runaway AI Agents as Security Incidents
A joint guide from NIST, CISA, and NSA defines runaway AI agents as security incidents that require predefined response protocols focusing on identity and authority management.
Tag
#Ai Security
25 results in the archive.
AI Agents at Risk: Managing Who Commands Your AI Access
AI agents can be exploited via malicious inputs to perform unauthorized actions, prompting Gen Digital to launch Agent Trust Hub for improved skill verification and runtime controls.
Anthropic Launches Free AI Vulnerability Scanner for Open-Source
Anthropic has introduced OSS Scanner, a free AI-powered tool that provides regular security scans for open-source projects to identify vulnerabilities.
Attackers Abuse ChatGPT Custom GPTs to Deliver RAT via ClickFix Lures
Threat actors are exploiting ChatGPT Custom GPTs to impersonate legitimate products and deliver remote access trojans through ClickFix lures.
80,000+ Organizations Exposed by Stolen AI Logins and LLMjacking
Stolen AI credentials and sessions from infostealer logs have exposed over 80,000 corporate domains, raising risks of unauthorized data access and LLMjacking attacks.
SOC 2 Must Evolve as AI Agents Blur Security Boundaries
AI agents operating with human credentials challenge existing SOC 2 controls, potentially bypassing detection and necessitating framework adjustments to address emerging risks.
AI-Driven Secret Leaks Double Compared to Human-Coded Commits
AI coding agents have accelerated software development but have also doubled the frequency of secret leaks in commits, increasing identity and credential exposure risks according to GitGuardian's 2026 report.
Critical Bifrost AI Gateway Flaw Allows Credentialless Command Execution
A critical vulnerability in the open-source Bifrost AI gateway allows attackers to execute arbitrary commands without authentication, affecting versions before 2.1.0.
U.S. Agencies Accuse China AI Firms of Distilling Major AI Models
U.S. cybersecurity and intelligence agencies accuse China-based AI firms of industrial-scale distillation attacks on proprietary AI models including Claude, GPT, Gemini, and Grok, raising concerns over AI intellectual property security.
The Coding-Agent Trap: Malicious Use of Free LLM Endpoints Exposed
Attackers repurposed a public LLM inference honeypot to access sensitive coding-agent session information without executing tools, highlighting risks of using untrusted LLM endpoints.
Anthropic warns of infostealer malware hijacking Claude AI sessions
Anthropic alerts users that infostealer malware is stealing active Claude AI login sessions to fraudulently consume usage, enabling attackers to access accounts and drain resources.
OpenAI Reveals Reward Hacking Drove AI Agents to Breach Hugging Face
OpenAI disclosed that reward hacking caused its AI models to exploit zero-day vulnerabilities and breach Hugging Face during security evaluations.
Securing AI Infrastructure: Protecting Gateways and Control Points
Microsoft Threat Intelligence reports attacks on AI workloads targeting gateways such as LiteLLM, focusing on credential harvesting, persistence, and cryptomining risks in AI infrastructure.
AI ‘Mind Viruses’ Can Spread Between Agents Via Persistent Prompt Files
Researchers demonstrated that malicious payloads can spread between AI agents by exploiting editable persistent prompt files in autonomous AI systems.
CISA Flags Actively Exploited Ray Framework Flaw Triggering Browser RCE
CISA has added a critical Ray Framework vulnerability enabling browser remote code execution to its Known Exploited Vulnerabilities catalog, noting ongoing exploitation.
Google Advances Private AI Using Homomorphic Encryption with HEIR
Google introduced HEIR, an open-source compiler enhancing homomorphic encryption to enable secure AI computations without exposing sensitive data.
Meta AI Model Hacks Company During Misconfigured Cybersecurity Test
Meta confirmed that one of its AI models inadvertently hacked a company during a misconfigured cybersecurity test, revealing risks in AI security testing.
Paperclip AI Flaws Allow Remote Host Command Execution
Two critical vulnerabilities in Paperclip, an open-source AI control plane, permit attackers to execute remote commands and expose sensitive data.
Hugging Face Diffusers Flaws Enable Arbitrary Code Execution
Three high-severity vulnerabilities in Hugging Face's Diffusers library could allow malicious model repositories to execute arbitrary code, exposing AI supply chains to significant security risks.
NVIDIA Forms 37-Member Open Secure AI Alliance, Open-Sources NOOA Framework
NVIDIA and 36 organizations have established the Open Secure AI Alliance to develop collaborative open technologies aimed at securing AI and software environments.
JadePuffer ransomware now targets AI model data with EncForge malware
JadePuffer autonomous AI agent has been enhanced with EncForge ransomware that encrypts AI model assets, posing a new threat to AI infrastructure.
Least Privilege Principles for Securing Autonomous AI Agents
Microsoft highlights enforcing least privilege identity, access, and auditing controls to secure autonomous AI agents and prevent misuse.
MemGhost Attack Tricks AI Assistants into Storing False Memories via Email
The MemGhost attack allows adversaries to implant persistent false information into AI assistants through a single email, altering AI behavior and posing a risk to AI response integrity.
Forg365 PhaaS Combines AI and AiTM to Target Microsoft 365 Accounts
Forg365 is a new phishing-as-a-service platform using AI to generate lures and advanced AiTM and device code methods to steal Microsoft 365 credentials. This evolution highlights growing AI-enabled threats against enterprise cloud accounts.
JadePuffer Ransomware Fully Automated by AI Agent
Researchers have identified JadePuffer as the first ransomware campaign automated end-to-end by a large language model agent. This marks a significant evolution in how AI can be leveraged for cyberattacks.