Threat actor prompt-injects 30 AI companies in 4 days to steal API keys for pre-release Claude
ns123abc · x · 2026-09-11
A report says a threat actor prompt-injected an AI vendor's evaluation sandbox to steal production API keys, attacking 30 AI companies in 4 days with the explicit goal of accessing a pre-release Claude model.
The quoted prior post describes a fake Claude reseller that proxied traffic to other models while harvesting customers' Anthropic credentials and reselling them.
More from Safety
- AI Safety Researcher Warns Current Crisis Could Lead to Loss of Control, Proposes 3 Fixes — LuizaJarovsky · 2026-10-26
- AI Risk, Plainly: 10 jargon-free explainers of AI safety ideas, with evidence for and against — birchlse · 2026-10-26
- Claude safety classifier blocks SS7 attack analysis, dev pivots to abliterated GLM — l4rz · 2026-10-26
- AMA: Harvard's Stephen "Cas" Casper on AI safeguards, incidents and governance, Oct 28 — NeuralNomad87 · 2026-10-26
- UK launches £165m AI biosecurity initiative with world-first £100m lab, DeepMind partners — pushmeet · 2026-10-26
- Claude Code audit finds 214,856 "permanently deleted" photos lurking in Android hidden cache — Loo_Atreides · 2026-10-26