Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In our last post, we introduced the Model Context Protocol (MCP), the "brain" or "mission briefing" that guides an AI agent's actions. Most security teams are just getting familiar with prompt injection, the equivalent of tricking an AI with a single, misleading command. But that's like stopping a pickpocket at the door when a master spy is already inside, rewriting the mission plans. As AI agents become autonomous, the attacks become more profound.

At the RSAC Conference this year, it seemed that every cybersecurity company had suddenly become an agentic AI company. According to such vendors, AI agents were the solution to every security problem keeping CISOs up at night. The audience, however, was understandably skeptical. Concerns over vendor promises fell into two camps. The first camp: companies that took whatever AI capabilities they had and slapped the word ‘agentic’ on them (aka ‘agent-washing’). Or even worse.

As companies embed AI models into their applications, they face risks that traditional security tools weren’t designed to catch, such as prompt injection, data leakage, model poisoning, and shadow AI. Addressing these threats requires a new class of security tools built specifically for AI specific risk.

Healthcare organizations need to be prepared for an increase in AI-assisted phishing attacks, according to Zack Martin, Senior Policy Advisor at Venable. In an article for HIT Consultant, Martin explained that AI has made phishing attacks more convincing and easier to launch, posing a heightened risk to healthcare organizations.

Threat actors can now use AI tools to automate entire attack operations, according to a new report from Anthropic. The company says an attacker abused its Claude AI tool to create a hacking and extortion campaign that compromised at least seventeen organizations. The attacker used Claude to conduct reconnaissance, initial access, malware development, data exfiltration, and extortion analysis.

AI agents are rapidly evolving from simple text generators into powerful autonomous assistants that can browse the web, book travel, and extract complex data on our behalf. This new “agentic” AI, which operates in a “sense-plan-act” loop, promises to revolutionize how we interact with the digital world.

As the summer winds down and conversation around AI Security heats up, the Snyk team is in full swing planning mode for a double-header this October—with the return of DevSecCon’s Flagship conference, focusing this year on Securing the Shift to AI Native, and serving as the founding partner of the inaugural AI Security Summit.

AI marketing platforms have exploded in popularity, becoming everyday tools for creative teams in enterprises worldwide. Platforms like Simplified AI offer marketers the ability to generate content, clips, and campaigns at scale. For CISOs and IT leaders, approving such services often seems straightforward: allow access, whitelist the domain, and enable the marketing team to innovate.