mobile-test

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs expected development tasks such as project structure analysis, test code generation, and the execution of official platform test runners. Its behavior aligns with its stated purpose of enhancing mobile application quality.
  • [COMMAND_EXECUTION]: The skill executes standard CLI tools for mobile development, including 'flutter test', 'npx jest', 'npx detox', 'xcodebuild', and './gradlew'. These commands are used for running test suites and are standard in mobile CI/CD environments.
  • [DATA_EXFILTRATION]: The skill records execution telemetry to a local file ('~/.claude/projects/skill-telemetry.md') if the directory exists. This is a local storage operation for performance tracking and does not involve transmitting data to external servers.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests project files (e.g., pubspec.yaml, package.json) and user-provided arguments to generate code. While it lacks explicit boundary markers for user input, the instructions provide a highly structured output framework and specific behavioral constraints that focus the agent on technical testing tasks, reducing the risk of accidental or malicious instruction override.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:58 AM
Security Audit — agent-trust-hub — mobile-test