character-sheet

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions and reference guides for character design workflows. It does not include any executable scripts, binary files, or automated installation procedures. It primarily serves as a prompt engineering framework for image generation endpoints.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill mentions model routing (e.g., to fal-ai or Google models), but these are standard API calls for image generation and do not involve executing untrusted code on the agent's host environment.
  • [EXTERNAL_DOWNLOADS]: The skill mentions downloading dependencies within a user's authorized setup if missing, but it does not specify any third-party or untrusted URLs. It relies on standard host tools (Python, Node, renderer).
  • [DATA_EXFILTRATION]: There are no commands or instructions for accessing sensitive files or exfiltrating data. The workflow focuses on generating and localizing image artifacts.
  • [PROMPT_INJECTION]: The instructions are clear and focused on the character design task. There are no attempts to bypass safety filters or override the agent's core instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 07:17 AM