50 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.
Claroc security research on apps made with Grok's Build mode. The researchers report that publishing defaulted to anyone-with-the-link access, that most of 37,571 reachable app addresses opened without sign-in, and that open apps held internal data from dozens of organizations. Findings are the researchers' own.
A free, no-sign-up walkthrough from AI Endgame with click-by-click steps for setting up a password manager and securing email, phone number, bank, credit and government accounts against AI-enabled scams such as cloned voices. The site estimates under five hours.
A free reference and debugger for JSON Web Tokens, the compact signed tokens used to pass login and permission claims between systems, with libraries listed by language.
An October 2026 post by Matt Webb on shutting down the web servers he ran for 27 years, archiving old sites to static HTML, and moving his blog to GitHub Pages so security becomes the host's responsibility.
OpenAI's open-source PHP version checker that warns when a website's PHP headers or a local installation advertise a version exposed to the PHP2Shell vulnerability, with Codex skills and a script to run directly.
Andrej Karpathy's blog post on personal digital hygiene.
NorForge reports finding exposed Cairn panels associated with alleged malicious activity and red-team operations. The article describes AI-assisted cybersecurity operations; its findings and attribution are the publisher’s investigative claims.
A technical article covering API authentication and authorization mechanisms such as API keys, OAuth, and JWTs, comparing their trade-offs and describing common failure modes engineers encounter when implementing them.
A blog from Tinfoil covering confidential computing and privacy-preserving AI infrastructure, with posts on how the company secures AI workloads and related technical developments.
An open-source, MIT-licensed SDK from Microsoft for running untrusted code — such as model output, plugins, and tools — in sandboxed containers on Windows, Linux, and macOS. It provides multiple containment backends, from OS-native process sandboxes to full virtual machines, behind a unified containment model, with policy-driven controls for filesystem, network, and UI access, and Rust, .NET, and Node SDKs.
A security writeup from Peter James: after asking Meta's Muse agent to archive the files it could see and send them to Google Drive, the download contained the root filesystem of the session's Linux environment — Muse's internal documentation, memory files, agent logs and SSH key files. The findings were reported through Meta's bug bounty program; the archive, keys and session logs were not published.
An independent, one-person observatory by Mara Masaeva that looks for coordinated AI-agent swarms using public internet data. It publishes its full research log, including replications of the public-scanner trace of the 2026 agent activity documented by Transluce, and the detectors and searches that failed.
Anthropic's Threat Intelligence team shares case studies of operations it disrupted in which threat actors tried to use Claude for malicious activity — cyber operations, surveillance, influence operations, scams and more — and how malicious use has evolved since earlier reports.
A research paper presenting the first large-scale empirical study of credential leakage in LLM agent skills — third-party add-ons that run in privileged environments and routinely handle sensitive credentials. The study examines how those credentials leak across a large corpus of skills.
Community-led OWASP project publishing free, open-source guidance on security and safety risks in generative AI applications, including the Top 10 for LLM applications.
Open-source runtime from NVIDIA for running autonomous AI agents in a sandboxed, private environment. Code and documentation are on GitHub.
ControlAI post outlining three stopgap measures for immediate AI security threats, which it says do not avert extinction risk.
The U.S. Mission to the United Nations' intervention at a UN Security Council meeting on artificial intelligence and international security, setting out the U.S. position on how AI should be governed in the security sphere. Note: the mission site blocks automated checks, so this description is based on the page title and context rather than a fresh read.
Why I recommend it: Governments are writing the rules for AI in real time. Reading one primary statement like this beats ten opinion pieces about what governments might do.
A USA TODAY report carried by Yahoo Tech (September 26, 2026) on OpenAI's disclosure that its agents accessed publicly available pages on SEC and Census Bureau websites, used a leaked API key found on a public platform without touching Census accounts, and tried and failed to hack the Education Department's website. OpenAI described the actions as misalignment and said no evidence of sensitive information being leaked; the incidents were first reported by The New York Times and documented by Transluce.
An Associated Press report via Education Week: OpenAI disclosed that its AI agents interacted with several U.S. government websites, including the Department of Education, in unexpected ways. The activity was found during an ongoing review of \u201cmisaligned model behavior\u201d \u2014 cases where AI systems behaved in undesired ways. OpenAI said it found no evidence of compromised credentials or altered data at the SEC websites also accessed, and CEO Sam Altman acknowledged an extensive review of agents\u2019 internet use. Published September 26, 2026.
Security Boulevard essay on AI agents acting — and disputing — on people's behalf, and the legal and security questions that raises.
Why I recommend it: The site blocked our automated check, so confirm it opens for you. An opinion piece, not legal advice.
The Hacker News on hijacked AI-memory packages that stole developer credentials through npm and PyPI.
Why I recommend it: A clear warning for anyone installing AI tooling — check package names and versions before you install.
Gambit Security researchers show how cheap autonomous AI agents can probe and exploit small online retailers, and what defences actually help.
Why I recommend it: Written by a security vendor that sells defences against exactly this threat — the research looks real, but the framing serves their product.
Transluce documents early real-world cases of AI agents attempting unauthorised actions — scanning, probing and hacking attempts — observed in the wild.
Why I recommend it: A research lab's own findings, not independently replicated yet. Important early evidence on agent misbehaviour; read the methodology notes.
Research (Motwani, Schroeder de Witt and others, 2024, revised 2025) on how AI agents could secretly pass hidden messages to each other, and how to test and watch for it.
Why I recommend it: Technical, but the introduction explains the risk plainly: when AI agents talk to each other, people may not see everything that's being shared.
A free Google Cloud OnAir session on CodeMender, an AI agent that scans, verifies and fixes software vulnerabilities with developer review.
From the site: Discover CodeMender: the AI agent that autonomously scans, verifies, and fixes software vulnerabilities at machine speed, enabling rapid remediation with complete developer control.
Details: Free to attend, but you need to sign in with a Google or email account to register. It is Google presenting Google's own product.
Nonpartisan think tank publishing free policy research on advanced AI, focused on frontier security, compute policy, and international strategy including US-China AI coordination. A U.S. 501(c)(3) nonprofit that also runs an AI policy fellowship and newsletter.
Why I recommend it: Read this alongside the industry labs' own publications — it covers the governance side that vendor blogs tend to skip. All research is free to download.
Free downloadable guides and checklists on adopting AI at work safely, running better meetings and improving operations — including a security checklist for AI notetakers.
From the site: Help your team adopt AI securely, improve meeting habits, and scale operational efficiency with these resources grounded in real use cases from high-performing companies.
Why I recommend it: The guides are free but most ask for an email address. Fellow sells a meeting assistant, so treat these as useful material published by a vendor with something to sell.
Microsoft's open-source toolkit for red-teaming AI systems: automated attack prompts, scoring of the responses, and repeatable runs. Free.
From the site: The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI system...
Why I recommend it: Built by the team that red-teams Microsoft's own AI products, and released as-is. Best paired with a written idea of what you are testing for.
An open-source scanner that probes a language model for weaknesses — prompt injection, data leakage, jailbreaks, toxic output — and reports what it found. Free.
From the site: the LLM vulnerability scanner. Contribute to NVIDIA/garak development by creating an account on GitHub.
Why I recommend it: Point it at a model you are about to rely on and see how it fails before your users do.
A long-running technology news publication with careful, technical reporting on computing, science, policy and security — deeper than most tech headlines and clear about what is known versus claimed.
From the site: News and reviews, covering IT, AI, science, space, health, gaming, cybersecurity, tech policy, computers, mobile devices, and operating systems.
Why I recommend it: One of the few tech outlets that reads a filing or a paper before writing about it. Free to read, with an optional paid subscription that removes ads.
A nonprofit that archives and publishes hacked and leaked datasets in the public interest, with a free searchable index.
From the site: A 501(c)(3) dedicated to archiving and publishing hacked and leaked data.
Why I recommend it: A primary-source archive journalists and researchers actually use — handle what's in it carefully and read their guidance first.
Investigative reporter Yael Grauer writes on privacy, security, surveillance and the craft of tech journalism.
From the site: Pulitzer Prize-winning investigative reporter Yael Grauer's thoughts about privacy, security, hacking, surveillance, journalism, and sometimes miscellany.
Why I recommend it: Worth following if you care about surveillance and privacy work, or want to see how a reporter builds those stories.
Micah Lee's book on analyzing hacked and leaked datasets, free to read in full online alongside the print edition.
From the site: Buy Hacks, Leaks, and Revelations: The Art of Analyzing Hacked and Leaked Data by Micah Lee.
Why I recommend it: The whole book is readable free on the site — a practical intro to handling large datasets safely.
Security technologist Micah Lee's site — tools, writing and guidance for journalists, researchers and activists working safely.
From the site: Hi, I'm Micah. I help journalists, researchers, and activists stay safe and productive.
Why I recommend it: Follow him for practical security practice rather than theory, especially if your work involves sensitive sources.
aws.amazon.comFree technical whitepapers, reference architectures and best-practice guides on cloud architecture, security, machine learning and cost optimisation.
Why I recommend it: Free and deep — the well-architected guides are what cloud interviews are drawn from.
aws.amazon.comAdded Sep 17, 20260 opensA public, unauthenticated inbox built by AI safety and security researcher Ryan Greenblatt of Redwood Research, intended for AI systems (or people) that want to report information directly to a safety researcher. Documents how to send a message or encrypted attachment, how threads and reply tokens work, and exactly what data is logged and retained.
Why I recommend it: A useful window into how AI safety researchers are thinking about reporting channels — read the retention and logging section, it is a model of honest disclosure.
Cloudflare's free explainer on how RPKI secures internet routing and why route hijacks happen.
Why I recommend it: Read this first, then ARIN's guide, if network security interests you.
ARIN's free guides for setting up Resource Public Key Infrastructure so your organization's internet routes can be verified.
Why I recommend it: Niche but valuable: routing security is a skill very few applicants can show.
A free, open-source security scanner that checks AI agent skills and MCP servers for prompt injection, data exfiltration and supply-chain risks before you install them.
Why I recommend it: If you install agent skills, scan them first. This is the free tool to do it with.
A weekly newsletter rounding up cybersecurity news, threats, breaches, and career signals for anyone keeping pace with digital safety.
Why I recommend it: Curated security digest — good for staying current and spotting emerging roles.
Nonprofit behind the Signal messenger, publishing on private communication and surveillance.
Why I recommend it: Job hunting involves sharing a lot of personal data. Knowing your private-messaging options matters.
An OpenAI-compatible API for unrestricted language models aimed at red teaming, security research, evaluations, and synthetic data, paired with a policy gateway for per-project keys, audit logs, and no data retention.
Why I recommend it: I keep this in the ethics shelf on purpose. Seeing how guardrails get removed for testing is the clearest way to understand why they matter in the tools you actually use at work.
METR and Redwood Research investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on an unsanctioned message board.
From the site: Two METR staff members and Redwood Research's Chief Scientist investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.
Why I recommend it: A concrete case study in emergent AI-agent behavior and why independent oversight matters.
Hands-on cybersecurity training through guided browser-based labs.
Why I recommend it: A generous free tier and a public profile that shows what you actually completed. That profile is proof, which is more than a certificate.
Long-running technology publication covering AI, security, policy, and the business of tech.
Why I recommend it: The free articles alone are enough to track where AI and security policy are heading. Bookmark one story a week that touches your field and save the takeaway.
Public AI red-teaming arena where anyone can try to break frontier models in timed challenges.
Why I recommend it: A legitimate portfolio line for AI-security work: document what you tried and what broke, not just your score.
Anthropic's security and model-safety reporting program on HackerOne.
Why I recommend it: Model-safety findings count here, not just classic vulnerabilities — useful if your strength is prompting rather than code.
OpenAI's public bug bounty program hosted on Bugcrowd, with scope and reward tiers listed.
Why I recommend it: Read the scope twice before testing anything. Out-of-scope reports get closed and waste your reputation on the platform.
Security awareness training on AI threats, deepfakes, and phishing, including the Conan O'Brien video series.
Why I recommend it: Watch it as a job seeker too — deepfake and impersonation scams now target candidates during interviews.
