Study: 1,404 email-agent instances hijacked in 2.03 tries on average
AryHHAry · x · 2026-09-01
Argues that bots managing school mail or closing listings are executing authority, not just assisting. Citing Wu et al. (arXiv:2507.02699), 1,404 email-agent instances were hijacked with an average of 2.03 tries, proving the inbox is an attack surface.
More from Safety
- Would OpenAI survive a near-miss liability regime after the HF hack? — dfrsrchtwts · 2026-09-01
- Report: OpenAI and Anthropic Paused RL Training — tszzl · 2026-09-01
- Scholars propose using LLMs for pre-review in academic peer review — anderssandberg · 2026-09-01
- Google Paper: Autonomous AI Research Hallucinates 90% Without Checks — rohanpaul_ai · 2026-09-01
- Paper defines cognition-induced risks in Agentic AI systems — 机器之心 · 2026-09-01
- Agents can't verify people: data enrichment APIs are failing — Dry_Steak30 · 2026-09-01