media-gemini-3-image-prompt

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely as a text-based prompt generator. It does not execute code, perform network requests to untrusted domains, or access sensitive local files. Its primary function is to transform natural language user input into structured image generation prompts using predefined templates and user-interactive questions.
  • [SAFE]: The external URLs provided in the SKILL.md and reference files all point to official Google developer documentation (ai.google.dev, cloud.google.com) or established technology blogs (medium.com, wavespeed.ai). These are used for information sourcing and do not involve remote code execution or data exfiltration.
  • [SAFE]: The skill mentions a sibling resource path ${CLAUDE_PLUGIN_ROOT}/skills/media-gpt-image-2-prompt/presets/. While it references local paths, this is a standard configuration for cross-skill data sharing within a platform environment and does not pose a directory traversal or privilege escalation risk in this context.
  • [SAFE]: The skill instructs the agent to use AskUserQuestion to gather user requirements, which is a standard interactive pattern for prompt builders and does not facilitate prompt injection or data exposure.
  • [SAFE]: No obfuscation, persistence mechanisms, or hardcoded credentials were found in the skill or its associated reference documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:41 PM
Security Audit — agent-trust-hub — media-gemini-3-image-prompt