Goblin
News
AI news, distilled.
|
News
About
News
About
Filtered by:
meta-prompt-guard-2
Clear
Titles
Summaries
7
Study: Public Benchmark Scores Poorly Predict How Prompt-Injection Detectors Perform on Real Agent Tool Outputs
Research
1
4d ago
7
Study: Public Benchmark Scores Poorly Predict How Prompt-Injection Detectors Perform on Real Agent Tool Outputs
Research
· 1 src · 4d ago
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
