'Give this prompt to your agents to protect yourself' flagged as attacker-style social engineering
kingslyj · x · 2026-10-22
Quoting a viral call to 'Give this prompt to your agents today to safeguard yourself. DO NOT WAIT!', basedjensen points out it reads exactly like what a bad actor would say — tricking users into feeding untrusted prompts straight into their own AI agents. He also quips whether people who no longer read code only write markdown or read it too. A cautionary example of prompt-injection-style social engineering disguised as security advice.
More from Safety
- AI Security Enters a Machine-Speed Arms Race, Human Patch Cycles Are Dead — srimisra · 2026-10-22
- Box CEO: Cybersecurity Will Be Where AI Creates the Most New Jobs — rakyll · 2026-10-22
- A frontier AI mutual insurer: proposal to make OpenAI and Anthropic mutualize catastrophic risk — scottleibrand · 2026-10-22
- PHP ships emergency fixes for two unauthenticated RCE bugs after embargo break — kingslyj · 2026-10-22
- Kelsey Piper inside Anthropic: Claude alone now outperforms human+AI at plotting bioweapons — tszzl · 2026-10-22
- AMA outlines path forward for FDA oversight of generative AI in medicine — HealthcareLdr · 2026-10-22