frontend-design

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts, including scripts/gemini_batch_process.py and scripts/media_optimizer.py, to perform core functions like asset generation, design analysis, and media optimization.
  • [PROMPT_INJECTION]: The skill processes untrusted user screenshots and design references to extract guidelines and generate implementation code, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided screenshots and design references (SKILL.md, references/design-extraction-overview.md).
  • Boundary markers: Absent. No delimiters are used to separate user-provided content from agent instructions.
  • Capability inventory: Subprocess calls to Python scripts that interact with external APIs and write to the local project structure.
  • Sanitization: Absent. The skill does not describe any validation or sanitization of the data extracted from images before it is used in subsequent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 10:22 AM
Security Audit — agent-trust-hub — frontend-design