personize-no-code-pipelines

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate integration templates and documentation for the Personize platform. All external URLs point to official vendor documentation or well-known services (n8n.io, google.com). There is no evidence of malicious code, data exfiltration, or obfuscation.
  • [PROMPT_INJECTION]: The skill defines workflows for processing external data (Indirect Prompt Injection surface). Evaluation of the surface reveals:
  • Ingestion points: Untrusted data enters the agent context via Webhooks (templates/webhook-to-personize.json) and CRM integrations.
  • Boundary markers: Not explicitly defined in the n8n templates (no specific "ignore instructions" delimiters), but nodes enforce structured data flow.
  • Capability inventory: The templates use n8n-nodes-base.httpRequest nodes to perform network operations against the Personize API.
  • Sanitization: Defensive coding in templates/webhook-to-personize.json includes input truncation and regex-based email validation to filter external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:33 AM