n8n-best-practices

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill recommends setting the environment variable NODE_FUNCTION_ALLOW_BUILTIN=*. This configuration disables default sandbox restrictions in n8n, allowing Code nodes to load any Node.js built-in module, including child_process and fs, which can be used to execute arbitrary system commands or access sensitive files.
  • [DATA_EXFILTRATION]: The documentation advises setting N8N_BLOCK_ENV_ACCESS_IN_NODE=false, permitting n8n Code nodes to access environment variables that may contain sensitive credentials. It also provides bash script examples for extracting API keys from .env.local files using grep and cut operations.
  • [PROMPT_INJECTION]: The skill documents an indirect prompt injection surface where untrusted data is processed with high-privilege capabilities.
  • Ingestion points: Untrusted data enters the agent context through the $input object in n8n Code nodes as described in the code snippets.
  • Boundary markers: The examples provided contain no boundary markers or instructions to ignore embedded instructions.
  • Capability inventory: High, as the skill explicitly encourages configurations that enable system-level command execution and file system access.
  • Sanitization: There is no evidence of sanitization or validation of external content before processing in the provided patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 01:38 PM