Avertissements

• Permission surface may require sandboxing
• Financial research output is not financial advice; require human review before any live investment decision
• The provided SKILL.md excerpt is incomplete; the full skill likely contains more detailed instructions, but the available content shows a clear workflow with references to companion files (checklist, components, styles) that ensure quality and consistency.
• Security: The skill instructs the AI to generate HTML with external resources (WebGL shaders, fonts, icons) via CDN or embedded assets, which carries a low supply-chain risk if endpoints are untrusted, but this is standard practice and no explicit dangerous commands or permissions are requested.
• Quality: The skill lacks explicit instructions on how to handle user-provided images or data validation, which could lead to inconsistent output if not covered elsewhere in the full documentation.
• Financial research output is not financial advice; require human review before any live investment decision.
• Permission surface needs review: shell or command execution, filesystem or document access
• Permission surface: shell or command execution, filesystem or document access

Méthode

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.