android-testing-unit

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes commands to run unit tests via ./gradlew and evaluate skill triggers with a local script scripts/eval_triggers.py. These are standard operations within the Android development environment.
  • [SAFE]: References are provided to official developer documentation from Google and the Kotlin project, which are recognized sources for development guidelines.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests user-provided code and requirements. * Ingestion points: User requests for test implementation are processed from the agent context. * Boundary markers: There are no explicit delimiters to isolate untrusted user data in the provided instructions. * Capability inventory: The agent can execute build commands and local scripts as defined in the examples. * Sanitization: The skill does not describe specific input validation or sanitization routines before processing user requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 05:01 AM