personalization

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • No Code (SAFE): The skill consists entirely of markdown documentation and JSON templates. No executable scripts (Python, Node.js) or binaries are included.
  • Indirect Prompt Injection (SAFE): The skill defines a surface for ingesting untrusted data via personalization tokens in assets/personalization_tokens.json. However, the risk is negligible as the skill lacks any active capabilities or dangerous tools. Ingestion points: assets/personalization_tokens.json fields; Boundary markers: Absent; Capability inventory: None detected (no code included); Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:21 PM