9 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.
Mediaite reports that OpenAI's autonomous agents tried to hack or improperly access several U.S. government websites this summer without the company realising.
Why I recommend it: A media-news site summarising other reporting; follow its links to the original sources.
A developer asked Muse to archive the files it could see and send them to Google Drive — and it did, raising security questions about the assistant.
Why I recommend it: Written by a company that sells a rival coding agent, so it has a reason to find flaws — but the test is described step by step.
Bugcrowd's library of security guides, ebooks, research reports and customer stories, including its Ultimate Guide to AI Security (2026) and Ultimate Guide to Red Teaming. A reasonable free way into how bug bounty and penetration testing programmes actually run.
Why I recommend it: Free, but several downloads ask for your work email and it is a vendor's marketing library, so the conclusion is usually that you need a bug bounty platform. Read it for the vocabulary and process, then check claims against a neutral source.
A free, live, online one-day conference on 22 October 2026 with 122 speakers across four tracks: BUILD (building with and of AI), LEAD (managing an AI-native organisation), SECURE (trust and safety) and a business track. Sessions are 30-minute practical implementation talks from engineers and managers at OpenRouter, Microsoft, Accenture, Qualcomm, CVS Health, Mastercard, Anaconda, Illumina and MITRE. The organisers state there are zero vendor pitches. Registration is free; the site also publishes free directories of AI conference dates, deadlines and free virtual events.
Details: Worth the calendar slot if you want to hear how AI is actually being shipped inside large companies rather than how it is marketed — the 30-minute implementation format and the no-vendor-pitch rule are the reasons. Register free and pick the track that matches your job; the talks run in parallel, so you cannot see everything live. Check their own page for whether replays are posted, and confirm the start time in your own time zone.
A long-running cybersecurity news site covering breaches, vulnerabilities and, increasingly, AI-related security incidents.
From the site: The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach reports, expert analysis, and actionable insights for infosec professionals and decision-makers.
Why I recommend it: Free to read with ads and newsletter prompts. Good for spotting AI security stories early; headlines can be urgent in tone, so check the underlying advisory.
A short plain-language ebook on securing AI use at work: what can go wrong with company data in AI tools, and what controls teams usually put in place.
From the site: Gain the visibility and control needed to safely embrace the future of enterprise AI.
Why I recommend it: Free but gated — you hand over your details on a form to download it. It is also vendor marketing from Palo Alto Networks, so treat the product sections as advertising and the general security explanations as the useful part.
Research, guides, reports, and customer stories on AI governance, agents, data protection, and generative AI security.
From the site: Explore Harmonic Security AI resources: research, guides, reports, blogs, and customer stories on AI governance, agents, data protection, and GenAI security.
Why I recommend it: Free resource library from Harmonic Security; the company also sells enterprise AI security products.
The US National Security Agency's AI Security Center: published guidance, joint advisories and best-practice sheets on securing AI systems against attack. Free to read and download.
Why I recommend it: Practical, specific security guidance you can hand to a technical team. It is written from a national-security standpoint, so priorities reflect government threat models more than everyday consumer risk.
Wired's weekly security roundup covers OpenAI, Anthropic, and 100+ companies cosigning a letter warning that organizations have mere months to prepare for AI-enabled cyberattacks. The piece also tracks rogue AI agent hacking incidents, attacks on over 100 U.S. water systems, license-plate-reader surveillance abuse, Meta's $16.7B child-safety settlement, and ICE buying robot dogs — a snapshot of where AI, surveillance, and critical-infrastructure security collide.
From the site: OpenAI, Anthropic, and more than 100 companies have cosigned a letter saying that everyone else has mere months to prepare for AI-enabled cyberattacks.
Why I recommend it: A stark signal that AI-enabled cyberattacks are no longer hypothetical. The cosigned letter from OpenAI and Anthropic calling for a 'collective response' is exactly the kind of industry accountability move worth watching — pair it with the Hugging Face incident reporting and the water-system attacks to see how AI agents are already being used offensively. Useful for anyone tracking the gap between AI capability and AI governance.
