algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses role-play instructions that direct the agent to emphasize "master-level implementation" and "deep computational expertise," which are intended to influence the persona and output style.
- [PROMPT_INJECTION]: The skill processes user-provided conceptual seeds to generate executable p5.js code, presenting a surface for indirect prompt injection.
- Ingestion points: User-provided inputs or instructions for the "Algorithmic Philosophy."
- Boundary markers: No explicit delimiters are used to wrap or isolate user-provided data.
- Capability inventory: Generation of interactive JavaScript (p5.js) code for artifacts.
- Sanitization: No validation or sanitization of user-provided conceptual input is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill fetches the p5.js library from Cloudflare's public CDN (cdnjs.cloudflare.com), a trusted well-known service.
- [SAFE]: No obfuscation, persistence, or data exfiltration mechanisms were identified in the skill code.
Audit Metadata