GRD-PER-01Tier IGuardrails & Safety Layers

Prompt Injection Defence (Layered)

Defend against prompt injection — direct and indirect — with layered controls at input, context-assembly, and output boundaries.

Runtime: PerceiveAgentOps: DeploySee on the matrix →
LAYERED PROMPT-INJECTION DEFENCE L1 · Input Scannerknown injection patterns L2 · Structural Separationdata ≠ instructions in context L3 · Intent-Constrained Toolsaction must match declared task L4 · Output Filterexfiltration patterns L5 · Least Privilegebounded blast radiusNo single layer is sufficient; defence in depth is the only workable posture.
In Plain English

This page is the complete instruction page for one pattern called "Prompt Injection Defence (Layered)." It explains the problem this pattern solves, the idea behind the solution, when you should (and should not) use it, and what happens afterward — both the good effects and the costs.

This matters because building AI agents is not just about making them clever. It is also about making them safe and predictable. Following a well-tested pattern like this one helps avoid common mistakes, and shows you exactly which safety rules and regulations it connects to, listed under "Standards Mesh" on this page.

Context

Prompt injection is the #1 LLM application threat (OWASP LLM01). Agents that read external content (emails, web pages, documents, tool outputs) face indirect injection: malicious instructions hidden in data the agent reads.

Problem

A single malicious string in an email or webpage can redirect an agent's actions.

Forces

  • Usefulness of external content vs trust assumptions
  • Detection rate vs false positives

Solution

Layer defences: (1) input scanners for known injection patterns; (2) structural separation of instructions from data at context assembly ("data goes here, instructions never change"); (3) intent-constrained tool invocation (the agent's action must match its declared task); (4) output filtering for exfiltration patterns; (5) least-privilege tool access.

Applicability

  • All agents that consume external content
  • Email, web, document, and browsing agents

Anti-Patterns

  • Single-layer defence ("we sanitise input")
  • Trusting tool outputs as if they were user input

Consequences

  • +Meaningful protection in depth
  • +Defeats most known injection vectors
  • Multiple layers to maintain
  • Sophisticated attacks still bypass