algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to define artistic concepts, which are then used to generate executable JavaScript. This creates a surface for indirect prompt injection.
- Ingestion points: User instructions inform the 'algorithmic philosophy' in SKILL.md.
- Boundary markers: The instructions mandate the use of the templates/viewer.html template as a fixed starting point for the code generation.
- Capability inventory: The skill generates interactive p5.js scripts for execution within a browser-based artifact environment.
- Sanitization: The skill relies on the AI agent's interpretation and constraints provided by the p5.js framework.
- Mitigations: Ensure that generated code is constrained to the p5.js context and does not include functionality for file system or network access beyond the sandbox.
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill's HTML template fetches the p5.js library from a well-known and trusted CDN.
- [DYNAMIC_EXECUTION]: The skill is designed to generate and execute p5.js code at runtime to create interactive art, which is the intended and standard functionality for generative art skills.
Audit Metadata