…Over 800 repositories pretended to be AI skills or MCP servers and appeared more than 600 times in public AI registries and catalogs. This increased the likelihood of being discovered by AI…
…Token Security discovers every agent, maps risky access, and automatically enforces intent-based policies. Scale AI safely without losing control or slowing down innovation. See it in action Why “Just Build It…
…The state of shadow AI in 2026 (and how attackers are taking advantage) AI adoption has exploded, but every new app, integration and extension introduces new threats and risks. The latest webinar…
…Where enterprise AI creates new exposure Not every AI application presents the same level of risk. AI assistants primarily retrieve information or generate content in response to prompts. AI agents go further…
New macOS malware embeds fake errors to confuse AI analysis tools By Lawrence Abrams June 25, 2026 12:23 PM A newly discovered macOS malware dubbed "Gaslight" is designed to confuse AI…
…Three more memory corruption security issues were discovered in the same six-hour code scanning session by researchers at AI-native security company DepthFirst AI. NGINX is a massively used web server…
…Waterfall coding practices were optimized for certainty in a world that was becoming increasingly uncertain. Discover Agentic AI Security Risks Before They Become Threats AI is making software creation possible at the…
…an AI agent in the past year, with 61% reporting exposure or mishandling of sensitive data as a result ( source ). Getting control starts with visibility. Security teams need AI agent discovery and…
…The campaign was initially discovered by Malwarebytes , whose researchers say that the 'Pro' installer is a trojanized copy of Claude that works as expected but deploys a PlugX malware chain in the…
…Token Security discovers every agent, maps risky access, and enforces intent-based policies automatically—so you can scale AI safely without losing control or slowing innovation. See it in action The Three…