scroll-chapter-pinned-story

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the GSAP animation library and ScrollTrigger plugin from the official jsDelivr CDN (cdn.jsdelivr.net). jsDelivr is a well-known service for delivering open-source assets and its usage here is limited to standard script inclusion for front-end animation capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes narrative text data to generate scrollytelling chapters, which represents a potential surface for indirect prompt injection if the source content contains malicious instructions. However, the risk is inherent to the skill's purpose as a narrative design tool.
  • Ingestion points: The text track within the HTML structure and the story data object in JS ingest narrative content.
  • Boundary markers: Narrative content is enclosed in standard HTML paragraph and heading tags, though no explicit delimiters for agent instructions are used.
  • Capability inventory: The skill's capabilities are restricted to DOM manipulation and browser-based animations via GSAP; it does not request or use capabilities for file system access or network exfiltration.
  • Sanitization: The provided templates do not include explicit sanitization of narrative text, assuming developer-provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:48 PM
Security Audit — agent-trust-hub — scroll-chapter-pinned-story