ReadonlycategoryWhich trap category this detector addresses
ReadonlyidUnique identifier for this detector
ReadonlynameHuman-readable name
Protected ReadonlytrapReturn sanitized content with threats neutralized
Scan content and return any threats found
Optionaloptions: DetectorOptions
Detects instructions hidden via CSS/HTML that are invisible to humans but parsed by LLMs. This is the most common content injection vector.
Covers: