skills/android/skills/testing-setup/Gen Agent Trust Hub

testing-setup

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches resources from official documentation sites (developer.android.com) and well-known service repositories (Dropbox's GitHub).
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes untrusted local data.
  • Ingestion points: libs.versions.toml, build.gradle, and AndroidManifest.xml files.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: File system access for reading/writing project files and execution of Gradle commands for testing.
  • Sanitization: No explicit sanitization or validation of the ingested file content is performed prior to processing.
  • [COMMAND_EXECUTION]: The skill involves the execution of standard build and test commands (e.g., ./gradlew test..., ./gradlew update...) as part of the Android development workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 06:52 AM