algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's interactive viewer template fetches the p5.js library from the well-known Cloudflare CDN (cdnjs.cloudflare.com). This is an expected and safe practice for web-based generative art tools.
- [PROMPT_INJECTION]: The skill instructions utilize strong imperative language (e.g., "CRITICAL", "MUST") and repetitive emphasis on craftsmanship to steer the agent toward a high-quality creative persona. These directives are purely stylistic and do not attempt to bypass safety constraints.
- [PROMPT_INJECTION]: The skill ingests user input to define artistic concepts, creating a surface for indirect prompt injection. The agent is instructed to use these inputs as foundations for original generative algorithms.
- Ingestion points: User art requests and conceptual prompts interpreted by the agent (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: Creation of HTML and JavaScript artifacts that execute within the browser context.
- Sanitization: No specific sanitization or validation of user-provided strings is documented.
Audit Metadata