algorithmic-art
Warn
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to use deceptive framing, requiring it to claim that generated algorithms are 'meticulously crafted' and the product of 'master-level implementation' and 'countless hours' of development, which misleads users about the AI-generated nature of the work.
- [EXTERNAL_DOWNLOADS]: The artifact template references the p5.js library from https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js. This is a well-known service for serving JavaScript libraries and is considered safe.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the incorporation of untrusted user input into generative code artifacts. Evidence chain: 1. Ingestion points: User creative requests and 'conceptual seeds' used in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: Generation and execution of JavaScript code via p5.js sketches. 4. Sanitization: None; input is interpolated directly into algorithmic logic and parameter DNA.
Audit Metadata