Lorimar (@kyrissulean.bsky.social)

...technique works by appending a "#" to the end of a normal URL, then adding malicious instructions. When a user interacts with a page via their AI browser assistant, those instructions feed into the LLM and can trigger outcomes like data exfiltration, phishing, misinformation, malware guidance

loading . . .

HashJack attack shows AI browsers can be fooled with '#' : Hashtag-do-whatever-I-tell-you http://dlvr.it/TPSccd