n8n-code-javascript
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions and code patterns for ingesting data from external, untrusted sources such as webhooks and other workflow nodes. This creates a surface where malicious instructions embedded in the processed data could attempt to influence the agent's code generation or subsequent workflow behavior.\n
- Ingestion points: Untrusted data enters the agent context via
$input.all(),$input.first(),$input.item, and$nodecalls, as detailed in thereferences/detailed-guide.mdfile.\n - Boundary markers: The provided code templates do not implement explicit boundary markers or delimiters to isolate untrusted input data from the surrounding logic.\n
- Capability inventory: The skill facilitates complex JavaScript operations, including data transformation, filtering, and aggregation across all sections of the
references/detailed-guide.mdfile.\n - Sanitization: The skill mitigates this risk by including an explicit 'Best Practices' section in
references/detailed-guide.mdthat mandates input validation and error handling before data processing.
Audit Metadata