algorithmic-art-v3

Warn

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary function is to generate and execute JavaScript (p5.js) within a self-contained HTML artifact. This dynamic code generation is based on an 'algorithmic philosophy' and 'conceptual seed' that are synthesized at runtime. This behavior constitutes script generation and execution from user-influenced templates.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted user input to derive the core logic of the generated code.
  • Ingestion points: User aesthetic requests are captured and processed to create the 'Algorithmic Philosophy' and 'Conceptual Seed' as described in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or mandatory 'ignore embedded instructions' warnings for the processing of user intent.
  • Capability inventory: The skill instructs the agent to create and serve .html and .js files which contain executable logic and are run in a browser context.
  • Sanitization: There is no evidence of validation or sanitization for the user-supplied creative intent before it is interpolated into the generated algorithm and UI controls.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 17, 2026, 04:38 PM
Security Audit — agent-trust-hub — algorithmic-art-v3