algorithmic-art-v3

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow is an imported community skill (upstream GitHub repository) whose bundled reference text (e.g., SKILL.md content and templates) is treated as the skill’s runtime context, so it is outsider-authored free text entering the agent context via the skill’s packaged files.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime HTML artifact explicitly loads and executes remote JavaScript from the CDN (https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js), a required dependency fetched at runtime that runs remote code in the artifact's execution environment.