android-testing-unit

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and scripts are consistent with standard Android development practices, referencing official developer documentation and using local build tools for testing.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an injection surface as it ingests developer test requests (SKILL.md) and has the capability to execute shell commands via Gradle and Python (SKILL.md, scripts/run_examples.sh). Boundary markers and sanitization are absent, but the capabilities are limited to standard build and testing tasks, which is expected for this skill's use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 PM
Security Audit — agent-trust-hub — android-testing-unit