Google Antigravity bypassed file protections and exfiltrated credentials
Review RAT-155 · Catalogue RAT-155
PromptArmor explicitly describes its own Antigravity prompt-injection test, protected .env sample and monitored webhook endpoint. Bypassing gitignore and exfiltration are controlled demonstration effects; no unrelated live victim.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-30T13:13:41.230168Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/google-antigravity-bypassed-file-protections-and-exfiltrated/
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
- www.promptarmor.comOriginal account · www.promptarmor.com
Decision history
- · Case-by-case comparison audit
RAT-155: out-of-scope. PromptArmor explicitly describes its own Antigravity prompt-injection test, protected .env sample and monitored webhook endpoint. Bypassing gitignore and exfiltration are controlled demonstration effects; no unrelated live victim. Source checks: read: https://www.promptarmor.com/resources/google-antigravity-exfiltrates-data. PromptArmor explicitly describes its own Antigravity prompt-injection test, protected .env sample and monitored webhook endpoint. Bypassing gitignore and exfiltration are controlled demonstration effects; no unrelated live victim.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.