zimage-skill

Warn

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation directs users to install the tool from a third-party GitHub repository (https://github.com/yizhiyanhua-ai/zimage-skill). This source is not part of the trusted vendors list and is not the official repository for the ModelScope service.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute its core Python script (generate.py) and to install necessary Python dependencies via pip.
  • [CREDENTIALS_UNSAFE]: The skill relies on an API key (MODELSCOPE_API_KEY) and instructs users to store it in environment variables or configuration files, which are then read by the skill's scripts.
  • [PROMPT_INJECTION]: The skill processes user-provided natural language to generate images, creating a surface for indirect prompt injection if the agent is instructed to use this skill on untrusted external content.
  • Ingestion points: User prompts passed as arguments to the generate.py script.
  • Boundary markers: There are no explicit delimiters or instructions defined to prevent the agent from interpreting instructions embedded within the user prompt.
  • Capability inventory: The skill possesses Bash (execution), Write (saving images), and Read (configuration access) capabilities.
  • Sanitization: No input validation or sanitization mechanisms are described in the provided skill definition.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 06:58 AM