AGENT LAB: SKILLS

n8n-code-javascript

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): Indirect Prompt Injection surface (Category 8) detected in README.md. Ingestion points: The skill describes processing untrusted external data via '$json.body'. Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands in the data. Capability inventory: The skill references network capabilities via '$helpers.httpRequest' and Node.js modules like 'crypto'. Sanitization: Stability checks are mentioned, but security-focused sanitization of input data is absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:39 PM