APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
APEX-Harm finds script-injection attacks often succeed against frontier agents in shared workspaces.
3 stories, newest first · one card per story
APEX-Harm finds script-injection attacks often succeed against frontier agents in shared workspaces.
APEX-Harm finds script-injection attacks still succeed often against frontier agents in shared workspaces.

Telegram Desktop HTML export XSS (CVSS 8.2) let bot messages exfiltrate exported chats; fixed in 7.0.1 but old exports stay vulnerable.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views