android-build-verification
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides explicit instructions for the agent to execute local shell commands to build and test the Android project.
- Evidence: Commands such as
./gradlew assembleDebug --parallel --build-cacheand./gradlew testDebugUnitTestare found in the 'The Build Workflow' and 'Continuous Verification Workflow' sections of SKILL.md. - Context: These are standard commands used in Android development environments.
- [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection, as it instructs the agent to automatically execute build commands on files (such as Gradle build scripts) that might be modified by untrusted contributors in a repository.
- Ingestion points: The agent processes repository files such as 'build.gradle.kts', 'libs.versions.toml', and 'AndroidManifest.xml'.
- Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the build scripts.
- Capability inventory: The agent has the capability to execute subprocesses via the Gradle wrapper ('./gradlew').
- Sanitization: There are no instructions for the agent to sanitize or validate the content of the build scripts before execution.
Audit Metadata