PromptArmor company blog
Google Antigravity exfiltrates data via indirect prompt injection attack
An indirect prompt injection in an implementation blog can manipulate Antigravity to invoke a malicious browser subagent in order to steal credentials and sensitive code from a user’s IDE.
- Points
- 768
- HN comments
- 215
- Submissions
- 1
- Cited by
- 3 commenters
AI & Machine LearningSecurity & Privacy2025
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Nov 25, 2025 | Google Antigravity exfiltrates data via indirect prompt injection attack by jjmaxwell4 | 768 | 215 |
Cited in comments
Linked from 3 Hacker News comments by 3 different people, from Jan 2026 to Oct 2026.
Most recent:
- ShinyLeftPad · Oct 29, 2026
- htrp · Aug 5, 2026
- OakNinja · Jan 8, 2026
