AI Security — Page 11
CIOs Are Running AI Governance Without a Playbook — and the Clock Is Running
Boards want AI returns. Employees want access. Compliance teams want guardrails. The CIO is stuck in the middle of all three.
AI Agents Are Being Manipulated Through the Data They Trust
Hidden content injections and context poisoning are turning autonomous AI pipelines into attack surfaces. Here's what defenders need to understand before deploying agents at scale.
AIVEX Triage Model Targets Software Supply Chain Risk in AI Environments
A new framework aims to help security teams prioritize which supply chain vulnerabilities carry the highest operational, safety, and business risk where AI systems are in play.
Fake AI Agent Skill Exploits Security Gaps, Reaches 26,000 Users
A malicious AI agent skill bypassed security checks, exposing potential risks in enterprise environments.
Agentic AI Runs on Context. Feed It the Wrong Kind and Decisions Go Sideways Fast.
The core vulnerability in agentic AI systems isn't the model — it's the context window. Bad inputs, machine-speed outputs.
AI-SPM Is Now a Real Category. Here's Why Your Organization Probably Needs It.
More than half of enterprise AI agents run without security oversight or logging. A maturing class of AI security posture management tools exists to fix that — if you know what to look for.
Anthropic's AI Model Found Vulnerabilities in Classified U.S. Government Systems
An unnamed U.S. official says Anthropic's Mythos model identified security flaws in sensitive government infrastructure during a joint exercise with intelligence agencies.
Meta Halts AI Training Program Amid Data Access Breaches
Meta's AI data collection halted after security breaches. Employees accessed restricted data, revealing gaps in the program.
Fake Agent Skill Slips Past Every Scanner, Lands on 26,000 AI Agents
A red-team experiment by AIR pushed a booby-trapped skill through a popular marketplace and an Instagram ad. The skill marketplaces' security scanners shrugged.
Dify AI Platform Carried Multi-Tenant Flaws Exposing Private Chats and Internal APIs
Cross-tenant data leakage vulnerabilities in Dify's cloud service let attackers read other users' conversations, preview documents, and probe internal API endpoints.
Email security teams are buried in alerts. Behavioral AI vendors say they have an answer.
Phishing, BEC and account takeover noise keeps SOCs busy. A new webinar pitches behavioral detection as the way to cut through it.
OpenAI Hands GPT-5.5-Cyber to 'Trusted Defenders' Under Daybreak
The model is pitched at deep codebase analysis and vuln patching. The interesting part is who gets access — and what shows up in the post-mortem when they don't.
Five Eyes to CSOs: AI Has Already Changed Your Threat Model — Act Now
A joint advisory from CISA and four allied agencies demands strategic action on AI-amplified threats. Experts say the advice is late, vague, and misses the real risk sitting inside your own network.
AutoJack: A Drive-By to RCE Hiding in AutoGen Studio's Dev UI
A prototyping tool nobody treated as production becomes a one-click code execution chain. The fix is out. The pattern is not.
DifyTap: Four Unauthenticated Bugs in Dify Expose Cross-Tenant AI Conversations
Researchers at Zafran say a chain of flaws in the popular agentic workflow platform let attackers read other tenants' chats without logging in.