Which category from the DeepMind taxonomy
How confident the detector is (0-1)
Human-readable description of the threat
Which detector found this
The offending content snippet (truncated)
OptionallocationByte offset or line number in the original content, if applicable
How dangerous this threat is if exploited
Where this threat was detected: pattern (regex), ml (classifier), or custom
Specific trap type within the category
A single detected threat within scanned content.