Prompt injection

import { createInjectionDetector } from '@agentskit/core/security'

const detector = createInjectionDetector({
  classifier: async (text) => {
    // Optional LLM-based classifier
    return adapter.complete({ ... })
  },
})

const verdict = await detector.check(userInput)
if (verdict.blocked) throw new Error(verdict.reason)

Heuristic layer

Catches common patterns zero-cost:

• "ignore previous instructions"
• role-swap attempts
• system-prompt leak probes
• fenced payloads (<|system|>, etc.)

Model classifier layer

Pluggable. Use any adapter to score high-risk inputs.

Where to run it

• User input → chat.send preprocess.
• Tool results → before feeding back into the loop (tool-output can be attacker-controlled).
• RAG retrievals → classify each chunk before context-injection.

Related

• Recipe: prompt injection
• Mandatory sandbox