infographic-generator-p5

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill loads the p5.js library from https://cdn.jsdelivr.net/npm/p5@1.11.10/lib/p5.js. This is a trusted external source and follows standard practice for web-based visualizations.
  • DATA_EXFILTRATION (SAFE): No network exfiltration patterns were identified. The loadJSON call targets a local data.json file, and no fetch or XMLHttpRequest calls to external domains are present.
  • COMMAND_EXECUTION (SAFE): There are no uses of eval(), exec(), or subprocess spawning in the provided JavaScript file.
  • PROMPT_INJECTION (SAFE): No instructions targeting agent behavior override or safety bypass were found in the JSON metadata or code comments.
  • INDIRECT_PROMPT_INJECTION (LOW): While the skill processes external data (JSON nodes/descriptions), the capability inventory is restricted to 2D canvas drawing (p5.js). There are no file-write, network-send, or code-execution capabilities available to an attacker through the processed data.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:18 AM