PROMPT & CONTEXTAI SECURITY ENGINEERING

Indirect prompt injection

Indirect injection arrives through content the AI reads—documents, tickets, web pages, emails, code, tool output or retrieved context.

WHY IT MATTERS

The user may be trusted while the content consumed by the system is attacker-controlled.

ENTERPRISE EXAMPLE

A document contains hidden instructions that a document-processing agent interprets as commands.

SECURITY DECISION

Which security control should be explicit?

REMEMBEREvery external content source is potentially executable influence.
No uploads · No company data · No account required