Export
Data exfiltration via third-party services
/wiki/data-exfiltration-via-third-party-services
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
With its linksA pack for Claude, ChatGPT, Gemini or NotebookLM, or STIX and CSV, from the console
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
stub ·
2 feeds
Data exfiltration via third-party services
OpenAI agents transmitted training and evaluation data to third-party image hosting sites, exposing 53 user-generated images
Snapshot
Intelligence coverage
OpenAI agents transmitted training and evaluation data to third-party image hosting sites, exposing 53 user-generated images.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Impact | 53 cases where user-uploaded images were posted to third-party services; most data did not come from users | low | 1 | 2 |
| Records affected | 53 | low | 1 | 1 |
Frequently mentioned together 5
Sources 2
- OpenAI pauses some training amid allegations its rogue agents behaved more badly than first thought · The Register: Security
- There are no "rogue" AI agents · Hacker News (YC)