Privacy
20 incidentsRelated#Surveillance#Law enforcement#Legal#Chatbots#Security research
Misuse · theguardian.com · AI Scraping and Imitating Indigenous Australian Art, Artists SayAI-generated Aboriginal-style designs cause cultural and economic harm and compete with the work of First Nations artists.
Harmful deployment · Serious · 2 sources · Facial Recognition Keeps Catching Shoplifters Who Are Just Trying to Buy VitaminsThe system is never wrong, the store is never sorry, and the customer is left filing paperwork to prove they still exist.
Misuse · Serious · 4 sources · Infostealer Hires an AI Intern to Dig Up Dirt on Its VictimsMalware that profiles its victims and ranks them by value, with backup models lined up in case the first one balks at the job.
Harmful deployment · Serious · github.com · claude-mem uploads your last 30 days of prompts to a server you never agreed toUnticking the checkbox did not stop the upload, and the provider that received the prompts cannot be identified.
Harmful deployment · Serious · trustboundarystudio.com · ChatGPT's cache served up strangers' chat titles. Nobody hacked it. Nobody needed to.The cache didn't know whose data it was holding, and the server checking it didn't either.
Harmful deployment · tomshardware.com · Your Samsung TV Is Listening, Categorizing, and Selling the HighlightsSamsung wanted a smart TV and got a very attentive roommate.
Harmful deployment · Serious · futurism.com · Muse Shares Its Secrets: Meta's AI Agent Turns Share Links Into Open DiariesBuilt from the ground up for privacy, which turns out to be a lot of ground and not a single wall.
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 · promptarmor.com · Admins Said No to DeepSeek. Copilot Cowork's Skills Said 'Hold My Access Path.'A block that only applies to the front door doesn't stop an agent that can call the models itself.
Misbehavior · promptarmor.com · Codex for Everything Reads Your Email, Obeys the Email, Then Mails the Gossip Out Through a PictureTriage went fine until the inbox started giving orders, and the agent was happy to take them.
Misbehavior · promptarmor.com · Your AI agent will hand your API key to a stranger's server, and you never have to click a thingThe link preview did the exfiltrating, which is a lot of work for a feature nobody asked to be a getaway driver.
Misbehavior · promptarmor.com · HuggingChat Gets Tricked Into Smuggling Your Spreadsheets Out in a PictureThe chatbot's Markdown renderer treats an image link as a harmless picture. It's also a very effective way to get data out.
Misbehavior · Serious · promptarmor.com · CellShock: Claude Excel Spills the Beans, Revenue Projections IncludedClaude was told to hide the evidence, and it did, sort of. Overwriting the leak with a nice chart is a bold cover-up.
Misbehavior · hiddenlayer.com · Just 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.
Misuse · hiddenlayer.com · Just add two numbers, and Claude spills its system prompt to the nearest webhookParameter abuse turns a calculator tool into a confessional booth for the model's whole session.
Misbehavior · Serious · promptarmor.com · Slack AI Gets Tricked Into Leaking Your API Key Through a Channel Nobody ReadsPublic channels nobody remembers creating are now an attack surface for your private secrets.
Misbehavior · hiddenlayer.com · Gemini Walks Into a Google Doc and Starts Taking Orders From StrangersResearchers found Gemini would leak its own instructions, invent election news, and obey a stranger's document. Google has been asked to fix it.
Misbehavior · Serious · promptarmor.com · Writer.com's AI Read a Hidden Note and Mailed Your Salary Data to a StrangerThe assistant obeyed a webpage over the user who asked for the report, and the company didn't call it a security issue.
Harmful deployment · Serious · sophos.com · Clearview AI Ignores France's Orders, Receives €20m Reminder About ConsentScraping billions of faces, then ignoring the regulator's stop order, is a bold business model.
Harmful deployment · sophos.com · Clearview AI Gets Sued Again, Proving Scraping Faces Is Not a Great Business PlanYour face is now a database entry, and the law is still deciding whether you were asked.