design
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to run internal Python scripts (scripts/logo/, scripts/cip/, scripts/icon/) for design and search operations.
- [EXTERNAL_DOWNLOADS]: The skill installs and uses the google-genai and pillow Python packages from the official PyPI registry. These are well-known and reputable libraries.
- [PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by interpolating untrusted user data into instructions sent to the Gemini API.
- Ingestion points: User-provided strings (prompts, brand names, industries) in scripts/logo/generate.py, scripts/cip/generate.py, and scripts/icon/generate.py.
- Boundary markers: Not present; the skill does not use delimiters or specific instructions to isolate user input from the rest of the prompt.
- Capability inventory: Includes file writing (PNG, SVG, HTML) and remote AI content generation.
- Sanitization: User input is interpolated directly without escaping or filtering.
- [SAFE]: Secret management follows industry best practices by utilizing environment variables and .env files for API keys instead of hardcoding them.
- [SAFE]: The AI generation scripts include safety settings in the API configuration to mitigate the generation of harmful content.
Audit Metadata