custom-preview-flow

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown instructions and static reference data aimed at product design. No malicious patterns or security risks were identified across all 10 threat categories.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill references the author's website (rijoy.ai) for context regarding loyalty platforms, but no sensitive data is transmitted or hardcoded.
  • [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided product requirements, it lacks any high-privilege capabilities (such as file system writes, network requests, or shell execution) that would make it vulnerable to exploitation via indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 10:05 AM