heart-sticker-imagegen

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a secure two-stage execution flow (request material → recommend style → wait for confirmation → generate), which prevents the agent from performing actions without explicit user consent.
  • [SAFE]: It utilizes built-in capabilities like image_gen and view_image rather than executing arbitrary external scripts or downloading remote code.
  • [SAFE]: Prompt templates are statically defined within the skill's reference files (image-styles.md, text-styles.md), ensuring that generation behavior is predictable and constrained to the intended artistic styles.
  • [SAFE]: The skill includes transparent handling of service-related keywords (e.g., "Print stickers"), providing a documented contact ID for customer support without performing hidden data exfiltration or deceptive redirects.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 08:34 AM
Security Audit — agent-trust-hub — heart-sticker-imagegen