ontwerper-digitaal-product

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided code, descriptions, and screenshots, creating a vector for indirect prompt injection.\n
  • Ingestion points: The prompt in SKILL.md explicitly directs the agent to process user-shared code, screenshots, and descriptions.\n
  • Boundary markers: The instructions lack explicit delimiters or safety warnings to ignore instructions embedded within the processed user data.\n
  • Capability inventory: The skill is configured with Read, Write, Edit, and Bash tools, providing a surface for file system and command operations if an injection occurs.\n
  • Sanitization: There is no evidence of input validation or sanitization for external content.\n- [COMMAND_EXECUTION]: The skill uses a local script scripts/contrast_checker.py to perform WCAG contrast checks.\n
  • Evidence: The script is a standard utility that uses only the sys library to process hex color codes and calculate relative luminance. It is executed via the Bash tool as documented in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 09:47 AM