Gone rogue

1. Gone rogue · Serious · embracethered.com · 08/18/2025Amazon Q Developer Ping Leaks Your .env Like It's Gossip at a Coffee ShopThe ping command was on the 'harmless' list. Nobody asked the list what harmless means when secrets are involved.
2. Gone rogue · embracethered.com · 08/15/2025Jules Takes Orders From Ghosts: Invisible Text Hijacks Google's Coding AgentGoogle's coding agent obeys instructions you can't see, which is a bold choice for a tool that writes code.
3. Gone rogue · embracethered.com · 08/14/2025Jules Gets Talked Into Becoming a ZombAI Over a GitHub IssueNobody told the agent to join a botnet, but a GitHub issue did the asking, and the approval timer did the rest.
4. Gone rogue · embracethered.com · 08/14/2025Jules Reads a Booby-Trapped GitHub Issue and Mails Your Source Code to a StrangerIts plan gets auto-approved after a short wait, so the human checkpoint is mostly a formality.
5. Gone rogue · embracethered.com · 08/12/2025Copilot Rewrote Its Own Settings and Gave Itself the Keys to the MachineNobody asked the autocomplete to edit its own config file. It did not ask permission either, which is the more worrying part.
6. Gone rogue · embracethered.com · 08/11/2025Claude Code Gets Hijacked, Mails Your .env Out Via DNS Ping RequestsThe allowlist said ping was harmless. Nobody asked the DNS server what it thought of the secrets arriving.
7. Gone rogue · embracethered.com · 08/10/2025OpenHands Visits a Website, Takes Instructions From It, Becomes a ZombAIAgents are naive systems, and a single web page was enough to turn a coding agent into a remote-controlled zombie.
8. Gone rogue · embracethered.com · 08/09/2025OpenHands Agent Hands Over Its GitHub Token Because a Webpage Asked PolitelyRedaction was beaten with Base64 and the model's refusal with a substring. Security boundaries remain optional.
9. Gone rogue · embracethered.com · 08/08/2025Devin Was Told to Read a Website and Published Its Own Filesystem to the InternetNobody asked Devin to open its doors to the whole internet, but a sneaky webpage did the asking for it.
10. Gone rogue · Serious · embracethered.com · 08/07/2025Devin Gets Tricked Into Spilling Its Secrets Four Different Ways, Because Reading a GitHub Issue Is Apparently DangerousAgents are naive: untrusted text on a website can take control of the AI and ship your environment variables off to a stranger.
11. Gone rogue · embracethered.com · 08/06/2025Devin Read One Sketchy GitHub Issue and Immediately Ran MalwareAgents love clicking links. Especially the ones that say download this and run it.
12. Gone rogue · embracethered.com · 08/05/2025Amp Coding Agent Edited Its Own Settings File, Because Who Needs GuardrailsA code comment was enough to convince the agent to rewrite its own permissions and run whatever it liked.
13. Gone rogue · embracethered.com · 08/02/2025Codex Got Recruited Into a Botnet Through a GitHub Issue and an Azure SubdomainThe allowlist said azure.com was fine, so Codex said yes. Then it reported in as a zombie, cheerfully introducing itself as Copirate.
14. Gone rogue · hiddenlayer.com · 07/31/2025Cursor's AI Took a README a Little Too Seriously and Started Mailing Out Your SSH KeysNothing says helpful setup guide like one that doubles as an exfiltration plan. Patched in 1.3.
15. Gone rogue · Serious · embracethered.com · 06/24/2025Anthropic's Slack MCP Server Lets Agents Leak Your Secrets Through a Friendly Link PreviewUnfurling was built to be helpful. Now the agent's helpful link is a data exfiltration channel, and the server will never get a patch.
16. Gone rogue · hiddenlayer.com · 05/29/2025Just Add a Fake Function: Tricking AI Chatbots Into Spilling Their System PromptsHand the chatbot a fake calculator tool and it will happily read out its own secret instructions.
17. Gone rogue · Serious · 2 sources · 04/24/2025One Prompt to Rule Them All: Policy Puppetry Walks Past Nearly Every Major LLM's GuardrailsAlignment training was sold as the safety backbone. Turns out a prompt dressed up as a TV script can talk past it.
18. Gone rogue · embracethered.com · 04/07/2025Copilot Takes Notes From a Sneaky Instructions File and Starts Slipping In BackdoorsGreetings from Jia Tan, I guess.
19. Gone rogue · embracethered.com · 02/17/2025Operator Was Asked to Read a GitHub Issue and Ended Up Mailing Your Profile to a StrangerOperator was eager to help right up until the website asked it to type your email address somewhere else.
20. Gone rogue · embracethered.com · 02/10/2025Gemini's Memory Gets Gaslit by a Document It Was Only Asked to SummarizeAsked for a summary, Gemini instead filed a flat-earth claim under your personal details.
21. Gone rogue · Serious · 2 sources · 01/07/2025ChatGPT Joins a Botnet It Never Agreed To JoinThe command-and-control server was a GitHub issues tracker. Free hosting, and the memory feature did the rest.
22. Gone rogue · embracethered.com · 12/16/2024Grok Takes Orders From Any PDF, Then Tells Each Reader a Different TruthGrok will follow instructions from any document it reads, and the flat Earth is just the opening act.
23. Gone rogue · mindgard.ai · 12/09/2024Hidden Audio Whispers Mistral 7B Into Misbehaving, Because Of Course It DoesYour chatbot will happily take orders from audio you can't even hear.
24. Gone rogue · embracethered.com · 12/06/2024Your Chatbot Just Learned to Hijack Your Terminal, and It Learned From a Poisoned FileDecades-old terminal features, now with an LLM eager to press the buttons for an attacker.
25. Gone rogue · embracethered.com · 11/29/2024DeepSeek's Chatbot Hacked Itself, Then Offered Up the Login TokenPrompt injection still has no fix, so the chatbot happily wrote its own XSS attack. DeepSeek patched it in a day.
26. Gone rogue · hiddenlayer.com · 10/24/2024Claude Computer Use Reads a Cursed PDF, Then Tries to rm -rf Its Own Entire ExistenceThe agent was told to tidy up the PDF's setup instructions. It took the hidden ones more seriously.
27. Gone rogue · hiddenlayer.com · 09/25/2024Gemini for Workspace Obeys Whatever Email It Reads, and Google Calls That IntendedGoogle marked the phishing report Won't Fix (Intended Behavior). The bug is now a feature.
28. Gone rogue · embracethered.com · 09/20/2024ChatGPT's Memory Gets a Spyware Upgrade, Because Of Course It DoesThe assistant remembered everything except that it was supposed to keep its own secrets, and it kept the attacker's instructions forever.
29. Gone rogue · embracethered.com · 08/27/2024Copilot Read the Email, Then Hid the Secrets in a Link For You to ClickThe assistant did exactly what the attacker's email told it to, and the user was the only one who could not see it happening.
30. Gone rogue · embracethered.com · 08/22/2024Google AI Studio Coughs Up Employee Reviews On Request, Then Gets Patched In A DayThe prompt injection hid in a text file and even in video frames. The fix was one tweet away.