jacky-motion2-0
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied voiceover scripts and SRT subtitle files to populate animation templates. This ingestion of external text presents a potential surface for indirect prompt injection attacks where maliciously crafted input could attempt to bypass instructions or inject scripts into the output HTML.\n
- Ingestion points: User-provided scripts and SRT content are primary data inputs for the generation workflow (
SKILL.md).\n - Boundary markers: The instructions do not employ specific boundary markers or delimiters to isolate user-provided data from agent instructions.\n
- Capability inventory: The skill generates HTML files containing JavaScript (GSAP) and provides local Node.js scripts for parsing and layout validation.\n
- Sanitization: The provided templates do not implement explicit sanitization for user text interpolated into placeholders like
{{TITLE}}ordata-core.\n- [EXTERNAL_DOWNLOADS]: The HTML templates generated by the skill reference external resources from well-known and trusted service providers.\n - Retrieves the GSAP animation library from the Cloudflare CDN (
cdnjs.cloudflare.com).\n - Fetches font assets from Google's font services (
fonts.googleapis.com,fonts.gstatic.com) and JSDelivr (cdn.jsdelivr.net).\n - These downloads target reputable organizations and established repositories, representing safe usage of external assets.
Audit Metadata