The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references the p5.js library from Cloudflare's well-known CDN in the templates/viewer.html file (https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js). This is a standard and safe practice for web-based tools.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes user input to define artistic themes. (1) Ingestion points: User requests are processed as foundations for the 'Algorithmic Philosophy' in SKILL.md. (2) Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. (3) Capability inventory: The skill generates and renders executable p5.js JavaScript code. (4) Sanitization: No explicit sanitization or escaping of the user-provided conceptual seeds is documented. Despite this surface, no malicious instructions to override safety guidelines were found.
[SAFE]: No evidence of hardcoded credentials, data exfiltration, persistence mechanisms, or obfuscated content was found across the provided files. The skill functions as a creative tool within the expected parameters.

algorithmic-art