n8n-code-python

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates and methods for ingesting data from external sources, creating a potential vector for indirect prompt injection where malicious instructions could be embedded in the processed data.
  • Ingestion points: The skill utilizes _input.all(), _input.first(), _input.item, _json, and _node to access data from preceding n8n nodes, as documented in SKILL.md and references/detailed-guide.md.
  • Boundary markers: The code templates do not implement boundary markers or instructions to isolate untrusted data from the agent's logic.
  • Capability inventory: Execution environment includes the Python standard library with modules for data transformation (e.g., re for regex, json for parsing, base64 for encoding).
  • Sanitization: There is no evidence of input validation or sanitization routines to prevent the execution of instructions that might be contained within the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 12:47 AM
Security Audit — agent-trust-hub — n8n-code-python