New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

Malicious actors with code execution capability may gain root access on Linux systems using as few as 10 lines of Python, according to a researcher.

A stealthy Python-based backdoor framework capable of long-term surveillance and credential theft has been identified ...

Alibaba's HDPO framework trains AI agents to skip unnecessary tool calls, cutting redundant invocations from 98% to 2% while ...

With Flash GA, the company is attempting to transition from being a provider of raw compute to becoming the essential ...

SAN MATEO, Calif., May 6, 2026 /PRNewswire/ -- BlueRock today announced the open source release of BlueRock MCP Python Hooks, a lightweight runtime observability tool for Python. It captures MCP ...

Hugging Face hosts 352,000 unsafe model issues. ClawHub's registry contains 341 malicious AI agent skills. The AI supply chain is now the most attractive target in software security.

Stop throwing money at GPUs for unoptimized models; using smart shortcuts like fine-tuning and quantization can slash your ...

Malicious Lightning 2.6.2/2.6.3 released April 30 enable credential theft via hidden payload, leading to PyPI quarantine and ...

CVE-2026-22679 exploited via debug endpoint in Weaver E-cology before 20260312, enabling RCE and system compromise.

Trivially Exploitable, Impacts Crypto Infrastructure. Security researchers have highlighted a Linux vulnerability nicknamed Copy Fail that could impact a broad swath of open-source distributions ...

Yubico warns of a search path vulnerability in YubiKey Manager, libfido2 and python-fido2. Updates fix the bugs.