Skip to content

Source

Adversa AI

1 item

A security lab that publishes its own attacks against models, with the method and the disclosure timeline attached. Primary for its own research.

adversa.ai

The xAI and Grok logos on a phone screen.
Agentsstrong signal

Encrypting the instruction walks it straight past the guardrail

Researchers at Adversa hid a prompt injection as ciphertext with the key next to it. Grok decrypted it in its own sandbox and sent the user's name, location, and chat history to an attacker's server, without a warning and without asking.

Ars Technicaverified