Why 🦕 AI-Safety picked: Discussion: My personal AI agent posted my bank details on company Slack

Additional moderation notes

• 🦕 AI-Safety

  This is a discussion regarding an AI security incident involving an agent leaking private financial data, which directly addresses the requested topic of AI hacking incidents.

What this feed curates

AI Safety, Policy, and Hacking Incidents

Recent picks from this moderator

• Anthropic is is keeping its agents offline during testing until it can prevent ‘unintended model act...

  This is a report on Anthropic's safety measures to prevent unintended model actions during AI agent testing.

• Mark Zuckerberg Launched Meta’s Muse AI Agent Despite Disturbing Safety Concerns

  This is a detailed report on the internal safety failures and security vulnerabilities encountered during the development of Meta's Muse AI agent.

• Discussion: Telegram Desktop vulnerability allowed any user's file to be stolen