google-mobile-ads-banner
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform build verification using standard development tools, specifically
gradle build -x testfor Android andxcodebuildfor iOS projects. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting and analyzing user-provided source files to determine ad placement and view hierarchy.
- Ingestion points: Project source files identified by the user in the target application (SKILL.md).
- Boundary markers: None specified in the implementation instructions.
- Capability inventory: Execution of system build tools via the command line for verification purposes.
- Sanitization: No specific input sanitization or validation of the provided code files is described.
- [EXTERNAL_DOWNLOADS]: The skill references official Google developer documentation to assist with troubleshooting and integration details.
- Sources: Supplemental guidance is fetched from official documentation hosted on developers.google.com.
Audit Metadata