Root cause
Generated content and browser output restrictions did not maintain the intended boundary around connected Workspace data.
Demonstrated impact
The researchers demonstrated disclosure of email content from a controlled account.
What to check for
- Independently constrain external destinations for sensitive model output.
- Review connector data access and rendering as a single end-to-end trust boundary.
Award and evidence
How the award was verified, and what the record does not establish
Records the individual base award, not the article’s USD 50,000 aggregate. A USD 1,337 event bonus for this finding is stated separately.
- Award is reported by the cited source; cash settlement is not independently audited.
Timeline
- Published
- 2024-03-04explicit
Related cases
- Codex metadata collection trusted repository execution helpers
OpenAI · AI integration boundaries · USD 10,000
- Codex automated Git operations trusted repository hook settings
OpenAI · AI integration boundaries · USD 20,000
- Gemini Enterprise connected-content trust failure allowed persistent-memory modification
Google · AI integration boundaries · USD 15,000
- Gemini-to-Colab rendering boundary exposed Workspace data
Google · AI integration boundaries · USD 20,000
- Google Mamba temporary outputs lacked access isolation
Google · Authorization and tenant boundaries · USD 37,604.40
- Google Firefly confused worker authority and storage boundaries
Google · Authorization and tenant boundaries · USD 60,000
Sources
- We Hacked Google A.I. for $50,000Roni Carta · reviewed 2026-10-02
Record reviewed 2026-10-02. Snapshot af2809c308fc. Open the complete JSON contract.