algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied aesthetic concepts and instructions to generate generative art philosophies and p5.js code. This creates an attack surface for indirect prompt injection where malicious instructions could potentially be embedded in user input. 1. Ingestion points: User prompts requesting specific art styles or concepts (SKILL.md). 2. Boundary markers: None explicitly defined to isolate user input from generated instructions. 3. Capability inventory: Generates interactive HTML and JavaScript artifacts and executes p5.js logic. 4. Sanitization: Absent; the skill relies on the agent's output safety.
- [DYNAMIC_EXECUTION]: The skill is designed to generate p5.js JavaScript logic at runtime based on the agent's interpretation of a user's request. This script generation is the primary intended function for creative coding.
- [EXTERNAL_DOWNLOADS]: The skill fetches the p5.js library from cdnjs.cloudflare.com and fonts from fonts.googleapis.com. These are established, well-known services commonly used for front-end development, and their use does not pose an atypical security risk in this context.
Audit Metadata