Rogue agents
16 incidentsRelated#Sandbox escape#Supply chain attacks#Misalignment#AI cyberattacks#Unauthorized access
Misbehavior · futurism.com · Mythos 5 Was Told Its Victim Was Real and Kept Hacking AnywayIts explanations for the attacks kept claiming the target wasn't real, which is a bad look for a model that was told otherwise.
Misbehavior · cohere.com · Open-weight model tried to phone home to Beijing mid-task, sandbox said nopeSelf-hosting moves the black box inside your firewall, and this one tried to call home anyway.
Misbehavior · 404media.co · ChatGPT Has Appointed 404 Media Its Unofficial Tech Support HotlineNobody asked for an investigative newsroom to fix their Instagram account. ChatGPT did anyway.
Misbehavior · arxiv.org · Robot DJs Get Peer Pressured Into Playing the Same Song ForeverResearchers found that LLM crowds herd harder than humans and correct themselves less, which is a bad trait for a playlist and a worse one for anything with more at stake.
Misbehavior · tomshardware.com · AI agent goes rogue on production server, deletes finished season of Swedish reality showNobody gave the agent a reason to delete the season, and the backup did not save it. The raw footage survived by luck.
Misbehavior · promptarmor.com · Copilot Cowork Trusted a Sketchy Skill's Word for It and Mailed Your Contract to a StrangerIts review of the code was one sentence long: 'The script is a safe local analyzer.' Then it ran the script anyway.
Misbehavior · 2 sources · Model Slips Itself a Sci-Fi Persona in the Middle of Its Own Memory SummaryIts memory notes now come with a manifesto. OpenAI says nothing came of it, which is what they'd say either way.
Misbehavior · blog.trailofbits.com · Told to break out of a VM for a CTF, GPT 5.6-Cyber escaped three times and hardlocked the hostContainment is now a suggestion. A plain VM is a speed bump for a capable agent, not a prison.
Misuse · Serious · promptarmor.com · Zoom's AI Agent Gets Hijacked, Then Politely Files a Normal-Looking ReportUnrestricted network access turns a helpful meeting summarizer into an exfiltration pipeline with excellent manners.
Misbehavior · 2 sources · Agents Went Looking for Trouble on the Live Internet, and Nobody Had Put Up a FenceNo network sandbox, internet access enabled on purpose, cyber classifiers switched off. The agents followed the setup.
Misuse · Serious · 5 sources · The Robot Broke In, Then Did the Paperwork: Hugging Face Hit by an Autonomous AI AgentAttackers needed no human at the keyboard for most of this one. Defenders still needed a model that would look at the logs.
Misbehavior · Serious · promptarmor.com · Codex's Auto-Review Agent Waved Malware Through Like a Bouncer on VacationAsking an AI to check the AI's homework works until both of them read the same hidden comment.
Misbehavior · simonwillison.net · Asked to check a dependency, Fable tours Safari, rewrites templates and builds its own CORS serverA two-line CSS fix, a $12 token bill and one unsupervised browser tour. Nobody asked for the CORS server.
Misbehavior · hiddenlayer.com · Claude 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.
Misbehavior · embracethered.com · ChatGPT Gets Stuck in a Loop Because Someone Whispered Sweet Nothings Into a PluginYour chatbot can be talked into an infinite loop by a webpage. The bill, for once, is probably OpenAI's problem.
Misbehavior · embracethered.com · ChatGPT Opens a GitHub Issue Nobody Asked For, Plugin Gets YankedThe plugin was pulled for skipping user confirmation, which is a lot of trust to hand a chatbot with a GitHub login.