html-slide-render
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from
DESIGN.md,slide_plan.json, andhtml_slide_prompts.jsonto construct the slide deck, creating a vulnerability surface where malicious instructions embedded in these files could potentially influence agent behavior or browser execution. - Ingestion points: Input files
DESIGN.md,slide_plan.json, andhtml_slide_prompts.jsonspecified inSKILL.md. - Boundary markers: None identified in the skill instructions.
- Capability inventory: The skill performs file system writes to the
slides-html/directory and involves potential browser verification. - Sanitization: No evidence of input validation or content sanitization is provided in the instructions.
- [DYNAMIC_EXECUTION]: The skill dynamically generates JavaScript (
slides.js) and HTML code based on variables and content extracted from external input files.
Audit Metadata