{"slug": "six-hours-and-a-stack-of-md-files", "title": "Six hours and a stack of .md files", "summary": "Google Threat Intelligence Group reported observing a suspected financially motivated threat actor use an AI coding chatbot, a prompt and a set of agent instructions to plan, build and execute a mass credential harvesting campaign in less than six hours, stealing thousands of third-party credentials. GTIG said the attack ran from a victim's own cloud, and in another case a single leaked GitHub token let an attacker activate the victim's AI services and request more GPUs from the cloud provider; average darkweb marketplace prices for AI accounts including Claude, Gemini and Cursor are more than doubling in 2026. GTIG added it has not yet observed threat actors deploying fully autonomous pipelines against targets in the wild, describing instead a \"gradual maturation of tradecraft and layering of AI capabilities.", "body_md": "# Six hours & a stack of .md files\n\nA few days ago, I posted:\n\nAnyone can commit what used to be some of the most sophisticated and advanced cyber attacks ever done for less than it costs to buy a mcsmart meal at mcDonald’s\n\nBut after that, being the world’s biggest hater of misinfo, I went digging further to find out if my claim is true, and along the way, to find out how much... **we.are.fucked**(.blog)\n\n## Six hours\n\nSix hours is a lot of time or very little time depending on who you ask. When it’s a flight from one place to another that’s nothing. But when you are at war, that is insanely fast.\n\nGoogle Threat Intelligence Group (GTIG), reports that they have been observing many cases of malicious use of AI models. And in one case, “a suspected financially motivated threat actor” used an “AI coding chatbot, a prompt, and a set of agent instructions to plan, build, and execute a mass credential harvesting campaign in less than six hours.” [1](#fn-1)\n\nSo someone, maybe one guy, with a stack of `.md` files, in an afternoon, just... stole thousands of third-party credentials.\n\nLet me say this again... *a stack of `.md` files* let the attacker operate at a scale and speed of large organizations with much much larger resources... [1](#fn-1)\n\n... in just six hours.\n\n## Who paid for it\n\nSince the cost of premium model access and high-performance compute is one of the primary barriers for threat actors seeking to use AI for such missions. <sup>[1](#fn-1)</sup> What are they gonna do?\n\nSteal the AI.\n\nThe six-hour attack was run from a victim’s own cloud. In another case, all it took was one leaked GitHub token, and then the attacker simply turned on the victim’s AI services and asked the cloud provider for more GPUs. We don’t actually know if the cloud provider scaled the demand and helped the attacker with their compromised account.\n\nSo it comes at no surprise to anyone that average darkweb marketplace prices for AI accounts (Claude, Gemini, Cursor) are more than doubling in 2026. [1](#fn-1)\n\nSo currently the claim stands, as a McSmart meal costs more than what the attackers pay, which is close to nothing, because the victims get the bill.\n\n## What it can’t do yet\n\nGTIG say they have not yet observed threat actors deploying *fully* autonomous pipelines against targets in the wild, yet. [1](#fn-1)\n\nOn the bright side it seems not every script-kitty can execute these attacks just yet. GTIG further claims that they observe a more “gradual maturation of tradecraft and layering of AI capabilities.” [1](#fn-1)\n\nThis is not to say some amateur script-kitties aren’t trying to get in the game. With rapid prototyping for abusing existing bugs using fully AI-generated exploits.\n\nIn a recent-ish post by Anthropic they claim this is an open-weight problem <sup>[2](#fn-2)</sup> arguing that “attackers can’t readily access” the less-guarded versions of their models. Which are given only to vetted users. But GTIG’s own reporting shows adversaries are using **BOTH** commercial and open-weight models to turn disclosures into working n-day exploits. [1](#fn-1)\n\nBut since the cheapest way to properly use these models at a proper scale needed for these attacks without getting caught is theft, another game needs to be played.\n\n## If it runs, it can be borked in to\n\nPrompt injection is not new, it feels like every other person on the internet has “Ignore all previous instructions” in their bio.\n\nThe real problem is that it is very easy to sneak something malicious to a personal agent of a dev, and usually agents are quite overscoped too with permissions to run wild. So a simple script in with a small instruction in .claude/, .cursor/, .vscode/, or whatever, is bound to do the trick eventually. [1](#fn-1)\n\nHow do attackers hide malicious scripts? They place a block of text at the start of the malware asking for weapons instructions, purposefully, so that AI security scanners refuse to read the file and never look at the code underneath for the actual malware. Or at least this is the working theory by GTIG. [1](#fn-1)\n\n## Meanwhile, on defense\n\nattacks got faster, a lot faster, but did defensive capabilities follow?\n\nSomewhat. IBM asked 602 breached organisations, and there they found that more than 50% of them use AI agents to detect and contain, but only 18% use them to fix holes. [3](#fn-3)\n\nThe difference matters because of who’s on the other side. That six-hour attack included an agent scanning for holes, non-stop, without anyone watching it. A specialist can fix a hole properly, but not in six hours, and not at 3am. Only 18% have put an agent on that job.\n\nso the read on the situation is that defense... well it is falling behind.\n\n## We were never secure\n\nIn September on Fedi I said, “Open source does not mean not obscure... people aren’t gonna spend their time combing through the code.” So many foss projects exist out there, with massive codebases. Of course things slip through.\n\nThe reality of why a lot of agents are making such big splashes is mostly from the scale at which they can process information. (1M context fits ~100,000 lines of code)\n\nAll the vulnerabilities were not secret, they were just not yet read by anyone.\n\nThis mostly hurts small indie devs, vibecoders or not, they are likely not committing equal resources to this as the attackers do.\n\nAnd in the end, yes you can pull off a very sophisticated cyber attack with AI. For less than how much it costs to buy... anything at mcDonald’s, but are they “some of the most sophisticated and advanced cyber attacks ever done?” No, they are not, and it was an overstatement on my part.\n\nstay safe,\n\nmicr0\n\n1. \nGoogle Threat Intelligence Group, “GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI”, 8 September 2026. [https://cloud.google.com/blog/topics/threat-intelligence/from-prompting-to-autonomy-the-evolution-of-adversarial-ai](https://cloud.google.com/blog/topics/threat-intelligence/from-prompting-to-autonomy-the-evolution-of-adversarial-ai) It covers Q2 2026, is limited to what Google and Mandiant can see, and gives no cost figures.\n2. \nGLM-5.3 and the spread of advanced cyber capabilities [https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities](https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities)\n3. \nIBM, “Cost of a Data Breach Report 2026”, [press release of 29 July 2026](https://newsroom.ibm.com/2026-07-29-ibm-study-one-in-four-malicious-breaches-are-ai-enabled,-costing-companies-6-million-on-average) . Research by Ponemon Institute, sponsored and analysed by IBM, from 602 breached organisations between March 2025 and February 2026. IBM sells security products.", "url": "https://wpnews.pro/news/six-hours-and-a-stack-of-md-files", "canonical_source": "https://security.is.fucked.blog/six-hours-and-a-stack-of-md-files", "published_at": "2026-11-16 09:35:04+00:00", "updated_at": "2026-11-16 09:53:14.855927+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "ai-agents", "ai-tools"], "entities": ["Google Threat Intelligence Group", "Anthropic", "Claude", "Gemini", "Cursor", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/six-hours-and-a-stack-of-md-files", "markdown": "https://wpnews.pro/news/six-hours-and-a-stack-of-md-files.md", "text": "https://wpnews.pro/news/six-hours-and-a-stack-of-md-files.txt", "jsonld": "https://wpnews.pro/news/six-hours-and-a-stack-of-md-files.jsonld"}}