Researchers have uncovered a supply-chain attack that hides in Python packages, propagates like a worm, and tricks LLM-based ...

AI agent exploited Salesforce sites; 263 objects, 55 Apex methods exposed at one portal, leading to PII and file leaks.

Anthropic's Mythos Preview was highly effective at finding vulnerability candidates, especially when analyzing source code.

Threat actors have struck the software supply chain yet again, this time hitting the Python Package Index (PyPI) with Mini Shai-Hulud in an attempt to spread poisoned code. In the latest campaign, ...

The Miasma supply chain campaign has sparked a fresh attack wave called Hades, this time involving 37 malicious wheel ...

TL;DR Introduction At the start of this year, I wrote a blog on how 2025 was the ‘year of the infostealer’, and it doesn’t ...

AI hackathon success stories: seven builders who won by making autonomous AI agents safer. OlympusOS, Deals Machine, Kraken ...

GreatXML, a new Windows BitLocker bypass exploit, targets a zero-day vulnerability in Microsoft Defender’s offline scan.

Attackers are actively exploiting CVE-2026-5027, a high-severity path traversal vulnerability in the AI development platform ...

Over 100 NPM and PyPI packages were injected with malicious code in the Miasma and Hades Shai-Hulud supply chain attack ...

Dozens of cryptographically verified open source packages from Microsoft were compromised late last week to add advanced credential-stealing code that was triggered when developers opened them in AI ...

Anthropic’s AI turned Firefox and Windows software patches into exploits within hours, including one Windows proof-of-concept ...