n8n-code-javascript
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting and processing untrusted data from external sources like webhooks and API responses, which constitutes a vulnerability surface for indirect prompt injection if the output is processed by an LLM without adequate sanitization.
- Ingestion points: Data enters the context via $input methods (e.g., $input.all(), $input.first()) and webhook nodes (nested under .body), as described in DATA_ACCESS.md.
- Boundary markers: The provided code snippets do not implement specific delimiters (e.g., XML tags or unique markers) to isolate external content from instructions in downstream LLM processing.
- Capability inventory: The skill documents high-capability functions including $helpers.httpRequest() for network operations and require('crypto') for cryptographic tasks in BUILTIN_FUNCTIONS.md.
- Sanitization: The skill mitigates risks by providing extensive documentation on input validation, null-handling, and normalization in ERROR_PATTERNS.md (Pattern #5 and Deep Dive) and COMMON_PATTERNS.md (Pattern #11 and #14).
Audit Metadata