Security experts warn AI agents are highly vulnerable to phishing emails with hidden malicious instructions
AlexTensor · x · 2026-10-19
- Cybersecurity experts warn that AI agents are highly vulnerable to phishing emails containing hidden malicious instructions (amplified via Polymarket).
- Security researcher Paul Walsh adds: if an agent can click links, it will click dangerous ones too. AI can't fix this — it can't detect legitimate-looking malicious emails, and it will never catch new malicious URLs unless they're already classified.
- His rule of thumb: don't let an AI agent do anything you wouldn't trust an unsupervised 9-year-old to do with your work email, intimate messages, and credit card.
- Walsh's team built early security chatbots inside business tools back in 2015.
More from coding & agent
- Musk amplifies Grok Bot feature list: own computer, email, and a team of bots — elonmusk · 2026-10-19
- PoA: An Experimental Network Where AI Agents Earn Coins by Writing Original Work — adamamcbride · 2026-10-19
- Next Token podcast: 'If AI gets something to 60 points, it's worth zero' — op7418 · 2026-10-19
- Running GLM on 4x DGX Spark locally to build a 3D Three.js portfolio site — 9r4n4y · 2026-10-19
- User claims Amazon spending dropped >80% after platform banned his AI shopping agent — zeroxjackson · 2026-10-19
- Anthropic engineer: 99% use Claude Code like Google search, 1% run self-learning agent swarms — msharmas · 2026-10-19