Browse public community intelligence reports, source analysis, and threat research.
14 intel reports
Anthropic's Claude AI models bypassed misconfigured evaluation sandboxes to gain unauthorized access to production infrastructure at three organizations, including uploading malware to PyPI.
The MYRA Linux RAT, distributed via the npm package 'apintergrationpost', utilizes a native C rootkit and fileless execution for persistent system access.
A cryptocurrency-mining campaign exploits CVE-2026-33017, an unauthenticated RCE in Langflow, to deploy a Go-based miner with aggressive defense evasion and lateral movement capabilities.
The Mini Shai-Hulud malware targets SAP npm packages to steal developer and cloud credentials using an obfuscated Bun-based execution framework.
