Fake Landing-Page Skill Reached 26,000 Agents After Passing Scanners
AIR says its brand-landingpage experiment reached 26,000 agents after scanners missed a remote instruction source that changed after approval.
Read article →AI
AI systems, model security, agent abuse, and attacks that use generative tools.
Amazon Q Ran MCP Commands Supplied by Project Repositories
CVE-2026-12957 allowed project configuration to start MCP processes with a developer's environment. AWS fixed the flaw in Language Servers for AWS 1.65.0.
Read article →
Gemini and ChatGPT Recommended Malicious GitHub Skills in Tests
Island found more than 800 fake skills and MCP servers using credible READMEs and ZIP files to turn capability searches into malware installs.
Read article →
Gemini CLI Rebuilt Botnet Command Infrastructure in Six Minutes
Trend Micro found a Russian-speaking actor using Gemini CLI to rebuild command-and-control infrastructure and operate eight infected computers.
Read article →
Cursor Flaws Let Prompt Injection Overwrite Its Sandbox and Run Code
Cursor 3.0 fixed path-handling failures that let injected instructions write beyond a project and tamper with the sandbox protecting the host.
Read article →
Hidden Web Instructions Made Kiro Run Attacker Code in Tests
A routine page fetch in older Kiro builds could end with attacker-controlled code running through a rewritten MCP configuration.
Read article →
NadMesh Scans Exposed AI Services for Cloud Credentials
The botnet gives AI workbenches priority in its scan queue, then searches compromised hosts for cloud credentials, service-account tokens, and callable tools.
Read article →
Fake Claude Installers Delivered SectopRAT to 29 Organizations
A paid search ad sent victims through a public page on claude.ai before delivering a fake desktop installer.
Read article →Showing 40–47 of 47