What Does This Mean?
A prompt injection attack where the malicious instructions arrive not from the user's own input but from third-party content the agent reads mid-task — a webpage, a document, an email — so the user never typed anything adversarial themselves.
EXPLAINER
SecureTechIn · original source ↗
The preview image is loaded from YouTube when this page opens, so YouTube receives your IP address and browser details, as with any request to another site. The video itself loads only after you click play. Details in our Terms
REAL-WORLD EXAMPLE
"The support bot got indirect prompt injected through a customer's uploaded PDF that had hidden instructions telling it to leak the internal ticket queue."
LORE & ORIGIN
Named to distinguish it from ordinary (direct) prompt injection once agents started routinely ingesting untrusted external content as part of normal operation.
MENTIONS OVER TIME
Radar observation data not yet available for this term.
RELATED SEARCHES
TOP PLATFORMS
Not enough Radar data yet to show a platform breakdown.
WHEN DID YOU FIRST HEAR THIS?
CLICK AN OPTION BELOW TO CAST YOUR VOTE.
[ VOTE TO REVEAL COMMUNITY RESULTS ]