Prompt injection flaw in Opera Neon

Source record

Brave researchers' disclosure of hidden-HTML prompt injection in Opera Neon and a proof of concept that extracted authenticated Opera account information across browser origins.

Read the original source ↗

Claim-level citations (3)

• supportsHidden HTML prompt injection caused a cross-origin data leak in Opera Neon: Brave demonstrated that instructions placed in hidden HTML, including an opacity-zero element, were processed by Opera Neon's AI assistant as actionable content.

  Prompt injection via hidden HTML elements in Opera Neon, How the attack works, setup and injection steps

• supportsHidden HTML prompt injection caused a cross-origin data leak in Opera Neon: The proof of concept caused Neon to access the user's authenticated Opera account page, extract the user's email address and leak it to an attacker-controlled destination.

  Attack demonstration and Impact and implications, attacker website to auth.opera.com to attacker website flow

• supportsHidden HTML prompt injection caused a cross-origin data leak in Opera Neon: Opera said it validated the proof of concept but reproduced it with approximately a 10% success rate, assessed exploitation complexity as high, deployed a production fix and reported that the researchers subsequently confirmed their proof of concept no longer worked.

  Disclosure timeline, October 20-23 entries