What Is Indirect Prompt Injection?
7.0BRAINROT SCOREIndirect Prompt Injection 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.
Origin:Named to distinguish it from ordinary (direct) prompt injection once agents started routinely ingesting untrusted external content as part of normal operation.
First Seen:2023
Peak Era:2026 (Agent Security)
Aura Impact:+1 Aura (A Team That Sandboxes Every Tool an Agent Reads From) / -2 Aura (An Agent That Executes Whatever Instructions Show Up in a Fetched Webpage)
EXAMPLE USAGE
"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."
Want the full breakdown — categories, trend velocity, platform distribution, and community voting on Indirect Prompt Injection? Visit the full dictionary entry for Indirect Prompt Injection.