skills/sharex/xerahs/build-android/Gen Agent Trust Hub

build-android

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use various command-line tools such as dotnet build, gradlew.bat, and adb to compile and install Android applications. It also uses Stop-Process to clear file locks, which is a standard procedure in resolving build conflicts.
  • [INDIRECT_PROMPT_INJECTION]: The skill monitors and analyzes output from build tools and error messages to identify issues like missing environment variables or locked files.
  • Ingestion points: Build logs and error output from standard development utilities (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary warnings are specified for the log analysis.
  • Capability inventory: The agent can invoke build commands and terminate processes based on the feedback from logs (SKILL.md).
  • Sanitization: The skill does not describe any sanitization of the logs before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:34 AM