html-slide
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (reference designs, source files) to generate workflow artifacts and executable code.
- Ingestion points: Processes external reference visuals and source documents to build DESIGN.md and slide_plan.json in SKILL.md.
- Boundary markers: No delimiters or safety instructions are defined for the agent when handling content from user-provided files.
- Capability inventory: The skill writes multiple files, including planning documents and full HTML/JS slide implementations to the workspace.
- Sanitization: No data validation or content sanitization is described for the input processing phase.
Audit Metadata