Prompt Injection Markers in AI Agent Tool Invocation Parameters

Ibrahim Saud@tektrix

•updated 6 days ago•0•0•0

This rule detects potential prompt injection attacks against AI agents by monitoring tool-invocation parameters. It identifies indicators such as common instruction-overriding phrases, large base64-encoded blobs, or embedded shell metacharacters within parameters when the agent's context is derived from external content (web, email, URLs, etc.).