creativeclaw-render-html-image
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied HTML and CSS which serves as an entry point for potential indirect instructions. Ingestion points: The html parameter in the render_html_image tool call accepts raw HTML/CSS input as defined in SKILL.md. Boundary markers: Instructions mandate explicit user requests for HTML rendering and require confirmation of visible copy and dimensions before processing. Capability inventory: The execution environment includes network capabilities through the inline_images feature and output generation via the render_html_image tool. Sanitization: No explicit sanitization or escaping instructions are provided for the user-supplied HTML content within the skill instructions.
- [SAFE]: The skill's external dependencies and network targets are restricted to the vendor's own domains (creativeclaw.co) or trusted public repositories (Google Fonts), representing legitimate operational functionality.
Audit Metadata