compose

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches source code for verification from official, well-known repositories including the Android Open Source Project (AOSP), Google's AndroidX GitHub repository, and JetBrains' Compose Multiplatform core repository. These sources are highly reputable and essential for the skill's stated purpose of providing accurate technical guidance.
  • [COMMAND_EXECUTION]: Employs environment-specific tools (MCP and CLI) to search documentation and lookup code symbols. These tools are used for read-only information retrieval from authoritative sources (Google's Android Knowledge Base).
  • [DATA_EXPOSURE]: The skill is designed to process user-provided design specifications, such as Figma frames and screenshots, to translate visual elements into code. While this represents an ingestion point for untrusted data, the processing is handled through descriptive translation rather than direct execution of the input content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:40 PM
Security Audit — agent-trust-hub — compose