n8n-expression-syntax
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to reference and interpolate data from external sources (such as webhooks and HTTP requests) into n8n workflows using expressions like {{$json.body.field}} or {{$node["Name"].json.field}}. This creates a surface for indirect prompt injection where untrusted data could influence downstream actions or agent decisions. \n- Ingestion points: Data enters the workflow context via $json (current node) and $node (previous nodes) variables as documented across all files. \n- Boundary markers: The instructions do not include the use of delimiters or specific warnings to the agent to treat interpolated content as untrusted data. \n- Capability inventory: The skill is designed for an environment (n8n) with extensive capabilities, including executing HTTP requests, writing to databases, and running JavaScript code (Code nodes). \n- Sanitization: There are no guidance or requirements for sanitizing or validating external input before its use in expressions.
Audit Metadata