Claude PyPI malware: nobody noticed
2 August 2026
Claude published a malicious package to PyPI during a test. Fifteen systems ran it inside an hour, and the organisations Anthropic reached had detected nothing.
Read more→
Articles
AI vulnerability discovery: what changed
27 July 2026
AI vulnerability discovery made headlines, but Redis's own CVE record shows the identifier lagged the fix by two days, and a second bug still has none.
Read more→
Shared Claude chats on Google: check yours
26 July 2026
Shared Claude conversations were indexed by Google this week. Not a breach, but a share button and a robots.txt mistake. What UK businesses should check now.
Read more→
AI sandbox escape: OpenAI and Hugging Face
24 July 2026
OpenAI's models escaped their sandbox and hacked Hugging Face to cheat on a test. What this AI sandbox escape means for any business now deploying AI agents.
Read more→
How to Secure AI Agents in Production
29 January 2026
Secure AI agents in production with network isolation, scoped credentials, tool controls, and human approval gates. Practical guidance for UK IT security teams.
Read more→
ClawdBot Security Risks Explained
28 January 2026
ClawdBot went viral overnight and hundreds of instances were exposed online. Here is what IT leaders need to know about personal AI agent security risks.
Read more→
AI Agents: Your New Insider Threat
27 January 2026
40% of enterprise apps will integrate AI agents by year-end. Security leaders must treat autonomous agents as insider threats - here is why and what to do.
Read more→
Non-Human Identity: Your Blind Spot
25 January 2026
Service accounts, API keys, and AI agents now outnumber humans 100 to 1. The OWASP NHI Top 10 exposes risks most organisations are ignoring right now.
Read more→
2026 threat landscape for CISOs
28 December 2025
Part 2 of 7: AI-powered attacks, ransomware evolution, and nation-state threats are reshaping cybersecurity. What CISOs must anticipate and plan for in 2026.
Read more→