Prompt injection

Typetechnique

Also known as: prompt-inject · indirect-prompt-injection

Technique inserting adversarial instructions into a model's input (often via user data or tool output) to override the system prompt's safety constraints.

4 mentions · 4 days · first seen May 28, 2026 · last seen Jun 12, 2026

DeclaredCo-mentioned in newsblue→red = more connectedClick a node for shared stories →

This graph shows co-appearance in news, not a confirmed formal relationship.

Connections

Co-mentioned co-mentionedGemini together 1× · GPT together 1× · Anthropic together 1× · Deepmind together 1× · OpenAI together 1× · Claude together 1× · Google together 1× · Federal Reserve (FED) together 1×

“Co-mentioned in news” means appearing in the same story, not confirmation of a formal relationship.

Timeline

June 2026 2 stories · 2 days
May 2026 2 stories · 2 days