android-code-review-expert
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard Android build system commands (
./gradlew) for verification purposes. - Evidence: The skill defines
./gradlew lintDebug,./gradlew ktlintCheck, and./gradlew testDebugUnitTestas verification commands. - Context: These commands are specific to the skill's primary purpose of code quality review and are standard practices in Android development environments.
- [PROMPT_INJECTION]: The skill processes untrusted external data in the form of code from Pull Requests, which presents a surface for indirect prompt injection.
- Ingestion points: Analyzing code diffs and files during pull request reviews (referenced in the 'When to Use' section).
- Capability inventory: The agent has the capability to execute shell commands (
gradlew) based on findings in the ingested code. - Boundary markers: The skill does not explicitly define delimiters or specific 'ignore embedded instructions' warnings for the code it processes.
- Sanitization: No specific sanitization or filtering logic is provided for the code content being reviewed.
Audit Metadata