card-creator

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for creating and editing card artwork (bank, transit, etc.) using an agent's image generation capabilities.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were found. The skill uses local asset paths for logo references (e.g., ../assets/logo-references/).
  • [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety filters, override system instructions, or extract system prompts. It includes legitimate behavioral constraints such as avoiding code-based drawing and providing appropriate legal disclaimers for third-party marks.
  • [OBFUSCATION]: Analysis of the text and metadata found no evidence of Base64 encoding, zero-width characters, homoglyph attacks, or hidden URLs. The use of Chinese characters in the logo reference index is legitimate for its international context.
  • [REMOTE_CODE_EXECUTION]: The skill does not perform any external package installations or execute remote scripts. It relies entirely on the host environment's image-generation tools.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied briefs and images, it has a limited capability set focused on image generation. It includes instructions to preserve user references and avoid publishing private data, which are good safety practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 01:08 PM