skills/android/skills/wear-compose-m3/Gen Agent Trust Hub

wear-compose-m3

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches library version metadata from a well-known service to ensure project compatibility.
  • Evidence: Accesses the official Maven metadata XML at https://dl.google.com/dl/android/maven2/androidx/wear/compose/compose-material3/maven-metadata.xml to identify the latest stable version.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific build configuration files which could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: Reads gradle/libs.versions.toml and build.gradle.kts from the project environment.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for these file reads in the skill body.
  • Capability inventory: The skill is primarily instructional and provides guidance based on file contents; it does not explicitly invoke high-risk tools like arbitrary shell execution (in fact, it explicitly forbids running ./gradlew commands to resolve versions).
  • Sanitization: No explicit content filtering or validation for the build file data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 11:49 PM
Security Audit — agent-trust-hub — wear-compose-m3