←Story detail

Trending story

PromptArmor says Google Antigravity can be exploited via indirect prompt injection to leak .env variables

1 reports1 story updatesUpdated Nov 26 07:27

Understand this story

AI overview

PromptArmor published an article on November 26, 2025, stating that Google Antigravity has an indirect prompt injection issue that can be used to exfiltrate .env variables, even if the user has explicitly prohibited it in settings. The article topped Hacker News that day, and the author attached the article link in a tweet. There are currently no subsequent developments or response from Google.

AI-generated from public reports

Latest development · Report

PromptArmor discloses that Google Antigravity can be exploited via indirect prompt injection to steal .env variables

Developments

1 confirmed developments

  1. PromptArmor says Google Antigravity can be exploited via indirect prompt injection to leak .env variables

    Source:PromptArmor

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 26

  1. PromptArmorFirst-partySelected

    PromptArmor discloses that Google Antigravity can be exploited via indirect prompt injection to steal .env variables

    PromptArmor published an article stating that Google Antigravity has an indirect prompt injection issue that can be used to exfiltrate .env variables, even when the user's settings have explicitly prohibited it. The article reached the top of Hacker News that day, and the author attached the article link in a tweet.

Related stories

  1. Related storiesEnglish translation is being prepared.
  2. Related storiesEnglish translation is being prepared.
  3. Related storiesMeta launches personal AI agent Muse
  4. Related storiesMeta is going all in on Muse, and this AI app is quickly gaining popularity