algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill references libraries from well-known and trusted providers. It fetches the p5.js library from Cloudflare's CDN and typography from Google Fonts.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of generating executable p5.js code based on user-provided artistic concepts. Ingestion points: User-provided prompts describing the desired art style or concept (SKILL.md). Boundary markers: None identified; the skill does not instruct the agent to use delimiters or warnings for user-sourced content. Capability inventory: The skill generates self-contained HTML/JavaScript artifacts that are executed in the user's browser (templates/viewer.html). Sanitization: The instructions lack specific guidance for the agent to sanitize or escape user input before it is interpolated into the p5.js scripts.
Audit Metadata