Critical disclosure: unauth to cross-tenant superuser on Fireworks AI
npinto · x · 2026-11-20
Researcher Nicolas Pinto shared a CRITICAL security disclosure report on Fireworks AI, describing an unauthenticated-to-cross-tenant-superuser vulnerability responsibly disclosed to the Fireworks security team. The post serves as a warning about trusting AI inference providers with multi-tenant isolation.
More from Safety
- California governor-elect Xavier Becerra floats criminal liability for rogue AI agents — ShakeelHashim · 2026-11-20
- Dutch Regulators Test 6 Smart Glasses Models, Find Medication Misreads and Unsafe Advice — Polymarket · 2026-11-20
- Appointing an EU GDPR representative still requires a signed paper letter, no digital signature — austinc3301 · 2026-11-20
- Clever phishing trick: fake 'mum' SMS asks you to save a new number — threepointone · 2026-11-20
- Caixin: US remote-access cutoff and Nvidia CEO exit leave China's tech giants halting overseas compute deals — Gregory_C_Allen · 2026-11-20
- Cryptographer Matthew Green questions why hack an inference provider to swap in an abliterated model — matthew_d_green · 2026-11-20