html-slide-render
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a legitimate and localized workflow for rendering slides from project files into a local folder. There is no evidence of network activity, credential harvesting, privilege escalation, or persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill implements a standard surface for indirect prompt injection by processing external data to generate executable HTML and JavaScript. 1. Ingestion points: DESIGN.md, slide_plan.json, and html_slide_prompts.json. 2. Boundary markers: Absent. 3. Capability inventory: Local file writing (slides-html/ directory). 4. Sanitization: Absent. This attack surface is consistent with the skill's primary function and is not paired with dangerous capabilities like network exfiltration.
Audit Metadata