banner-design
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes Python scripts (search.py, gemini_batch_process.py) and Node.js scripts (screenshot.js) located within the .claude/skills/ directory. These are used for searching design prompts, batch processing image generation, and capturing screenshots of HTML-based designs via Chrome DevTools.
- [EXTERNAL_DOWNLOADS]: The skill uses the Chrome browser to navigate to Pinterest for design research and utilizes Google Gemini models for generating visual assets.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves ingesting visual and textual data from Pinterest for art direction inspiration. While this constitutes an external data ingestion surface, the risk is localized to design references and the skill includes instructions to maintain security boundaries.
- [SAFE]: No obfuscation, credential exposure, persistence mechanisms, or unauthorized remote code execution patterns were found. The skill follows established patterns for multi-skill coordination within a local environment.
Audit Metadata