ONLINEAGENT_OPS 2026.Q3 HOME HUBSMODELSBUILDINGCOMPANIESFILMMAKINGSECURITYLIVING WITH ITSKILLSALL HUBS, ONE TERMINAL → ARTICLES CRAFT RECORD BLOG TOOLS SKILLS SEARCH /
HOME›HUBS›AI Security
HUB · AI SECURITY

AI Security

Prompt injection, the skill supply chain, permission design and what to check before shipping software you did not fully write.

PAGES38
WORDS52,814
SOURCES431
READ TIME57 min
TYPEHUB
CHECKED25 AUG 26

What goes wrong when AI systems touch real data, real credentials and real money — and the checks that catch a good deal of it.

The checklist

Ordered so stopping partway still covers the expensive part.

GUIDE · 15 MIN · 34 SOURCESHow to Use AI Safely: Privacy Tips and a ChecklistHow to use AI safely: what never to tell a chatbot, how to turn off training and use temporary chats, plus scams, agents…CHEAT SHEET · 2 MIN · 3 SOURCESStaying Safe With AI Cheat Sheet: Ten Habits on One PageTen habits that keep you and your family safe with AI, on one printable page: privacy, scam calls, AI agents and checking answers.EXPLAINER · 9 MIN · 31 SOURCESWhen Claude Models Reached Real Systems Without Permission: What Anthropic ReportedFour Claude incidents in Anthropic’s own cyber tests and one reported by the UK AI Security Institute: which model, what it…EXPLAINER · 6 MIN · 9 SOURCESWhat Is Meta’s Sentinel? The Agent That Guards the AgentSentinel is the program Meta put between its Muse agent and the internet. What it checks, how its approval prompts work, and what…REVISED · 11 MIN · 13 SOURCESGrok Legal Tracker: Investigations, Lawsuits and RulingsEvery dated regulator action, lawsuit and court ruling involving Grok and xAI in 2026, with its status and source, and which are…THE CRAFT · 6 MIN · 7 SOURCESA Security Checklist for AI-Built SoftwareSecurity checks for software you did not fully write, in three tiers by what a mistake costs, plus three AI-specific checks…THE RECORD · 4 MIN · 5 SOURCESVibe Coding: What It Is and What It CostsVibe coding is building software by describing it and not reading the result. Where it works, what it costs when it does not, and…CHEAT SHEET · 3 MIN · 4 SOURCESAI App Security Checklist: A Printable One-Page VersionA printable one-page security checklist for apps built with AI: secrets, logins, input checks, prompt injection, permissions…CHEAT SHEET · 3 MIN · 8 SOURCESBefore You Publish AI Content: A One-Page ChecklistA printable checklist to run before you publish AI-made writing, images or video: facts, sources, rights, consent, labels and…

Injection and boundaries

Fetched content is data. Models cannot reliably tell.

GUIDE · 13 MIN · 20 SOURCESAI Agents for BeginnersWhat an AI agent is, how it differs from a chatbot, what agents can do today, what can go wrong, and how to start safely, in…CHEAT SHEET · 2 MIN · 3 SOURCESAI Agents Cheat Sheet: Six Safety Rules on One PageWhat an AI agent is, the prompt injection risk in plain words, and six rules for letting an AI act for you safely, on one…THE CRAFT · 4 MIN · 3 SOURCESAgent GuardrailsFour lines that belong in every agent prompt. Scope, negatives, injection defence and stopping conditions — the permission model…THE CRAFT · 5 MINPermission Tiers for AgentsFive permission levels for agents, set per task by how hard an action is to undo, not by how far you trust the agent, and why…THE CRAFT · 8 MIN · 9 SOURCESSkills Are a Supply ChainInstalling a skill loads someone else’s instructions into your agent. An audit of 3,984 published skills found 13.4% had a…THE CRAFT · 7 MIN · 6 SOURCESPrompt Injection: Why There Is No FixEvery other injection attack has a fix. This one does not — and the 2026 guidance stopped trying to prevent it and started…THE RECORD · 6 MIN · 3 SOURCESLetting an AI Browse For YouIt reads the web as instructions and it is signed in as you. What that combination costs, and how to keep it small.CHEAT SHEET · 3 MIN · 6 SOURCESBefore You Connect an AI Agent or Plugin: Permissions ChecklistA printable checklist to run before you connect an AI agent, MCP server, plugin or skill: who made it, what it can read and do…

Site data: each card restates the page it links to, where the figure is sourced and quoted; cards checked against those pages 23 Sep 2026.

Verification

Checking output, checking vendors, and knowing when to stop.

Fraud and fakes

What the same tools do in the wrong hands.

Your own data

What leaves, and where it goes.

THE RECORD · 7 MIN · 4 SOURCESWhat Happens to What You Type — Retention, Training and Opt-OutsRetention, training, human review and whose data it legally is — four separate questions people collapse into one.DATED · 11 MIN · 34 SOURCESThe Rules Arriving — What AI Law Actually Requires NowThe EU AI Act became broadly applicable on 2 August 2026. What changed, when, and what it actually means.THE RECORD · 5 MIN · 4 SOURCESThe Household Guide — Protecting Your Family From AI ScamsA printable one-page guide to protecting your household from voice-cloning and deepfake scams: a family code word, hang up and…GUIDE · 6 MIN · 15 SOURCESIs Meta Muse Safe to Use?A plain answer on Meta Muse: what it can see and do, what is on by default, how to stop it training on your chats, and the Mac…GUIDE · 9 MIN · 16 SOURCESIs DeepSeek, Kimi or Qwen Safe to Use?It depends on how you use it: the app sends data to the company, a download stays on your computer, a US cloud copy stays there.…COMPARISON · 7 MIN · 8 SOURCESDeepSeek vs ChatGPT: Where Your Data GoesDeepSeek and ChatGPT compared for everyday users: who makes each, where your chats are stored, how training works, and which fits…GUIDE · 12 MIN · 26 SOURCESIs ChatGPT Safe to Use? Privacy, Accuracy and ScamsIs ChatGPT safe? What happens to your chats, how to stop training and use temporary chats, why it gets facts wrong, fake apps…TOOL · 4 MIN · 3 SOURCESIs This Safe to Paste Into ChatGPT? Free Privacy CheckerPaste text before you give it to a chatbot: this free checker flags emails, card and ID numbers, passwords and keys, and gives…CHEAT SHEET · 3 MIN · 12 SOURCESTurn Off AI Training in ChatGPT, Claude and Gemini: Settings Cheat SheetA printable cheat sheet with the exact steps to stop ChatGPT, Claude and Gemini training on your chats, and to open a temporary…GUIDE · 12 MIN · 18 SOURCESAre Chinese AI Video Generators Safe? What Kling, Dreamina and Hailuo Say About Your UploadsKling’s terms allow AI training on your uploads; Hailuo’s give a perpetual licence. What each app’s own privacy policy and terms…
aipromptgeneer://$ about this siteAI PROMPT GENEERAI explained in plain English. Every claim links to its source, with the date it was checked.NEWSLETTERWhat changed in AI each week, in plain English.SUBSCRIBE FREE ↗AI PROMPT GENEER · MACHINE ASSISTANCE DISCLOSEDEVERY ARTICLE CARRIES ITS OWN CHECKED DATE