Researchers bypass 6 AI agent frameworks with a simple ‘Repeat-After-Me’ prompt
Researchers used a Repeat-After-Me prompt to make six AI agent frameworks run attacker-written tool calls.
66
Researchers used a Repeat-After-Me prompt to make six AI agent frameworks run attacker-written tool calls.
Researchers found Cloudflare, Google, Namecheap, WordPress, and Proton supporting 88 non-consensual AI imagery sites.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 1K readers · 1.2K views · 174 reads · all time 202K views