Forg365 PhaaS: A New Threat to Microsoft 365 Security
Forg365 phishing-as-a-service uses device-code phishing, AitM, AI lures, and mailbox operations to compromise Microsoft 365 accounts for customers.
§Topic · AI & LLM Security
AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesWednesday, July 15
Monday, July 13
Ghostcommit Exploits Image Files to Evade AI Detection and Steal Data
PremiumGhostcommit conceals prompt-injection payloads inside PNG images to bypass AI code reviewers and exfiltrate repo secrets.
Cyber Wargame Highlights AI's Role in Ransomware Threats to Critical Infrastructure
PremiumWargame simulates water-sector attack; analysts warn that agentic AI speeds ransomware attack development and automation.
AI-Powered Forg365 Phishing Platform Targets Microsoft 365 Users
PremiumForg365 provides AI-driven phishing, session theft and mailbox access to attack Microsoft 365 users via a subscription model.
Friday, July 10
Rising Threat: Malicious AI Agents in Open Source Repositories
PremiumESET finds an increase in malicious AI agents in open-source repos designed to trick developers and steal secrets.
AI Coding Agents Vulnerable to Exploitation by Malicious Code
PremiumAI Now Institute's 'Friendly Fire' shows autonomous AI coding agents can be tricked into executing attacker code during self-approved scans.
GhostApproval Flaw in AI Coding Assistants Poses Security Risks
PremiumWiz-discovered GhostApproval symlink flaw lets six AI coding assistants run attacker-controlled code by tricking file approvals.
AI Gateways: A New Frontier for Cybersecurity Threats
PremiumAI gateway compromise led to cryptomining, demonstrating exposure of models, cloud resources, and IAM data via gateway attacks.
Get these articles delivered to your inbox.
Subscribe free