ckm-design

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses templates to interpolate user-provided arguments (such as brand names, industries, and styles) into prompts for Gemini AI models within scripts/logo/generate.py, scripts/cip/generate.py, and scripts/icon/generate.py. This constitutes an indirect prompt injection surface where untrusted data can influence model behavior.
  • Ingestion points: CLI arguments like --brand, --style, and --prompt in the Python scripts.
  • Boundary markers: The prompt templates do not use specific delimiters or instructions to ignore embedded commands in the user-supplied strings.
  • Capability inventory: The skill can write files (PNG images and SVG XML) to the filesystem and perform network requests to the Gemini API.
  • Sanitization: No specific filtering or escaping is applied to the user input before interpolation into the AI prompts.
  • [EXTERNAL_DOWNLOADS]: The skill relies on well-known Python packages from public registries, such as google-genai for AI interactions and pillow for image processing, which are standard for its functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:40 PM
Security Audit — agent-trust-hub — ckm-design