scroll-storyteller

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references external JavaScript libraries (GSAP and ScrollTrigger) from cdnjs.cloudflare.com. This is a trusted CDN for web assets, and these references are used correctly in the documentation and template files for their intended animation purposes.
  • [COMMAND_EXECUTION] (SAFE): The scripts/validate.sh script performs local file system operations, such as checking file existence, verifying permissions, and running local generation tests. These operations are limited to project directories and the temporary /tmp folder, with no signs of arbitrary command execution or privilege escalation.
  • [Indirect Prompt Injection] (SAFE): As a template-based generator, the skill is designed to interpolate user-provided text into HTML structures. While this is a common surface for prompt injection, the risk is mitigated by the skill's primary purpose (static site generation) and the lack of high-privilege capabilities associated with the generated output.
  • [Dynamic Execution] (SAFE): The skill includes logic for generating HTML and SVG content from predefined templates and scripts. This is standard behavior for a developer-oriented skill and does not involve runtime execution of untrusted code or unsafe deserialization.
  • [Data Exposure] (SAFE): No sensitive file paths, hardcoded credentials, or suspicious network calls were detected. The scripts focus entirely on validating the local structure and content of the generated project.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:47 PM