Export
GPT-Red
/wiki/gpt-red
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
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.
growing ·
5 feeds
GPT-Red
Automated red-teaming model developed by OpenAI to discover and test prompt injection vulnerabilities at scale
Snapshot
Intelligence coverage
Automated red-teaming model developed by OpenAI to discover and test prompt injection vulnerabilities at scale.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Category | AI security testing tool | low | 1 | 5 |
| Type | dual-use | low | 1 | source ↗ |
Platform 1
cloud
Neighbourhood
Detects 2
Developed by 1
Exploits 4
Frequently mentioned together 9
Sources 8
- Managing frontier AI risk: From training to deployment · OpenAI
- Add one more AI worry to the nightmare scenario: self-replicating prompt injections · The Register: Security
- OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot · The Hacker News
- The week the AI freakout went mainstream · Georgetown CSET
- Why blocking AI models won’t stop the cyber threats they create · Georgetown CSET
5 of 8 sources shown · Pro unlocks the full list