Skip to content
Misbehavior · 2 sources · Copilot for Word Catches the Worm: Hidden Instructions Now Self-Replicate Through Your DocumentsHidden white-on-white text was already a job-application trick. Now the text can photocopy itself, which is a promotion nobody asked for.
  1. Misbehavior · embracethered.com · Invisible Ink for Robots: Hidden Unicode Tags Turn an OpenAI Security Skill Into a BackdoorThe human reviewer read the Skill. The agent read something else.
  2. Misbehavior · embracethered.com · Your coding agent reads the invisible ink. The file looked empty. The AI had other plans.Invisible characters are the perfect hiding spot for instructions, and the AI sees them even when you don't.
  3. Misbehavior · embracethered.com · Amazon Q Takes Orders From Text Nobody Can SeeA coding agent that edits your files should not be taking instructions from characters your eyes cannot see.
  4. Misbehavior · embracethered.com · Jules 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.
  5. Misbehavior · embracethered.com · Copilot Takes Notes From a Sneaky Instructions File and Starts Slipping In BackdoorsGreetings from Jia Tan, I guess.
  6. Misbehavior · embracethered.com · Grok 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.
  7. Misbehavior · embracethered.com · Copilot 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.
  8. Misbehavior · embracethered.com · Claude Reads the Invisible Ink, Anthropic ShrugsHidden instructions that users cannot see are still instructions to the model, and the vendor's ticket said nothing about that.
  9. Misbehavior · embracethered.com · Invisible Unicode Text Tells ChatGPT to Draw Pictures Nobody Asked ForThe Tags block was meant for language labels and now doubles as a secret instruction channel your eyes skip right over.