New research and reporting highlight how indirect prompt injection and agent memory can create persistent insider-style risk, while coding agents remain susceptible to prompt-driven unsafe actions. Adjacent cybersecurity updates, including CISA KEV additions and critical flaws in self-hosted platforms, reinforce that classic exploitation paths still underpin most AI compromise scenarios.
The FBI warns of rising AI-assisted fraud, Microsoft tightens guidance on secure token handling for AI agents, and adjacent cybersecurity trends highlight KEV remediation and post-holiday phishing risks that affect AI environments.
The flip side of risk-based security Defenders have long used machine learning to sort CVEs by risk. Adversaries feed those same datasets into their own models, along with exploit proofs of concept, Shodan results, tech blog posts, and even your… Read More ›
Overview Every organization faces thousands of vulnerabilities, but not all are equal. Security teams use risk-based prioritization to decide what to patch first. Now, attackers are using AI to do the same — but in reverse. AI-assisted vulnerability prioritization allows… Read More ›