plan-avatar-app

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to conduct a structured interview with the developer to create a project brief for an 'Atmee' avatar app. It follows a provided question bank in references/questions.md.
  • [EXTERNAL_DOWNLOADS]: The skill references https://github.com/Atmanity/atmee-ai-demos for inspiration. As this is the official repository of the skill's author (atmanity), this is considered a safe vendor resource for fetching documentation and architectural patterns.
  • [COMMAND_EXECUTION]: The YAML frontmatter includes allowed-tools: Bash(*/update-check*). This is a restrictive configuration that limits the skill's access to a specific update-checking utility within the ecosystem, rather than granting broad shell access.
  • [REMOTE_CODE_EXECUTION]: The skill uses a Model Context Protocol (MCP) tool at https://api.atmanity.us/mcp. This is a standard transport mechanism for AI agents to interact with specific service APIs. The domain atmanity.us belongs to the skill's author and is used for account management, limits, and pricing checks as described in the documentation.
  • [NO_CODE]: The skill provides instructions and references but does not ship with executable scripts (e.g., .py or .js files). It relies on existing platform tools like atmee-setup and build-avatar-app.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 12:15 PM