StoryFirst seen
Autonomous AI agents running on commercial assistants show how attacks on banks and other financial companies can scale.
Everything it touches
4 names 1 voices 1 source posts
The story’s neighborhood
Explore the graph, or choose a connection below.
Follow the evidence
This brief comes from Tech Twitter’s edited headlines. The posts below are the sources grouped with the story; statements in them belong to their authors.
Hackers turned Claude and Grok into a network of AI agents that autonomously targeted more than 400 financial institutions and other financial targets, according to cybersecurity research shared with The Information. Read more:Read original on X
Hackers used Claude and Grok agents to attack over 400 financial firms
Hackers Used Claude and Grok to Attack Over 400 Financial Firms
Shared connections
The findings show a model under test can talk itself past clear safety limits, which matters to any company deploying autonomous AI agents.
Lab results cannot be reset like a password, so exposed records carry lasting risk for patients.
Anyone holding that key could impersonate websites, putting nearly every site users visit at risk.
Risky actions will be blocked automatically instead of requiring approval for each step, which changes how most users work with the assistant.