skills/n8n-io/n8n/config-evals/Gen Agent Trust Hub

config-evals

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the setup of LLM-based evaluations that ingest and process data from external datasets and workflow outputs, which presents a surface for indirect prompt injection.
  • Ingestion points: Data enters the evaluation context via data-tables (test datasets) and workflow node outputs (specified by endNodeName).
  • Boundary markers: The skill uses n8n expression syntax ={{ $json.<field> }} to reference data. The instructions mandate the use of the = prefix to ensure values are treated as expressions rather than literal strings, though this does not prevent injection within the resolved content.
  • Capability inventory: The skill utilizes the eval-config tool (actions: create, update, list, get, delete) and data-tables tool (actions: list, create, insert) to manage evaluations and their associated data.
  • Sanitization: There is no explicit requirement or mechanism described for sanitizing or filtering the content of the workflow outputs or dataset columns before they are passed to the judge models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:37 AM
Security Audit — agent-trust-hub — config-evals