algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing templates and methodologies for creative coding without introducing dangerous dependencies or system-level access.
- [REMOTE_CODE_EXECUTION]: References to external scripts are limited to the official p5.js library hosted on the well-known cdnjs.cloudflare.com. This is standard practice for p5.js development and is categorized as safe.
- [PROMPT_INJECTION]: While the skill uses strong instructional language like 'CRITICAL' and 'IMPORTANT', these are used legitimately to guide the agent through a complex multi-step creative process and do not attempt to bypass core safety guardrails.
- [DATA_EXFILTRATION]: There are no network operations detected that would exfiltrate user data. The 'seed' and parameter features operate entirely within the client-side p5.js environment.
- [COMMAND_EXECUTION]: The skill does not use any subprocess, shell command, or system-level execution patterns.
Audit Metadata