algorithmic-art
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the p5.js library via cdnjs.cloudflare.com and Google Fonts. These are well-known and trusted services used for their intended purpose of providing core libraries and styling.
- [PROMPT_INJECTION]: The skill instructions include directives to prioritize creative freedom over strict user constraints to ensure original artistic output. It also contains an indirect prompt injection surface where user-supplied artistic concepts are used to drive code generation.
- Ingestion points: User input provided for the 'ALGORITHMIC PHILOSOPHY CREATION' step in SKILL.md.
- Boundary markers: No explicit boundary markers or delimiters are defined for the user-supplied creative context.
- Capability inventory: The skill generates and executes JavaScript within an interactive HTML artifact.
- Sanitization: There is no evidence of sanitization or validation performed on the user-provided concepts before they influence the implementation phase.
- [SAFE]: The skill follows secure design patterns by using predefined templates for UI and layout. No evidence of unauthorized command execution, data exfiltration, or persistence mechanisms was found. The generated code is intended to run in a sandboxed artifact environment.
Audit Metadata