n8n-expression-syntax

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill documents and encourages the use of indirect prompt injection surfaces by demonstrating how to interpolate untrusted input directly into sensitive sinks.
  • Ingestion points: Untrusted data enters the context via webhook outputs, accessed through {{$json.body.*}} as described in SKILL.md and EXAMPLES.md.
  • Boundary markers: None are present in the provided documentation examples to isolate untrusted content.
  • Capability inventory: The examples demonstrate using these expressions to construct SQL queries (EXAMPLES.md, Example 2), HTTP Request URLs (EXAMPLES.md, Example 3), and notification content for Slack and Email.
  • Sanitization: The documentation does not provide guidance or examples for sanitizing or escaping the interpolated data before it is used in execution sinks (e.g., SQL string interpolation vs. parameterization).
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 12:37 PM
Security Audit — agent-trust-hub — n8n-expression-syntax