Anti-bot scripts weaponize AI safety guardrails with toxic function names

A researcher scraped 10,000+ sites and found anti-bot scripts deliberately naming functions after ricin and bioweapons, tricking AI assistants into refusing to help analyze the fingerprinting code.

2026-10-29 ~ 2026-10-29 · 2 related posts

• Anti-bot scripts hide ricin-dose function names to trip AI safety filters — matthew_d_green · 2026-10-29
• LLM biorisk refusals weaponized as obfuscation, potentially raising cyber risk — nlarusstone · 2026-10-29