google-mobile-ads-interstitial
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions in
references/android-interstitial.mdandreferences/ios-interstitial.mddirect the agent to usegradle build -x testandxcodebuildrespectively to verify the ad implementation. - [EXTERNAL_DOWNLOADS]: The skill fetches troubleshooting documentation from Google's official developer domain (
developers.google.com). - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where untrusted external data could influence agent behavior due to the combination of ingestion and execution capabilities.
- Ingestion points: Content is retrieved from
https://developers.google.com/admob/android/next-gen/interstitial.md.txtandhttps://developers.google.com/admob/ios/interstitial.md.txtwhen internal knowledge is exhausted. - Boundary markers: The instructions lack explicit delimiting or warnings to ignore instructions that might be embedded in the external documentation.
- Capability inventory: The agent is authorized to execute shell commands for building projects (
gradle,xcodebuild). - Sanitization: There is no evidence of sanitization or validation logic for the external content before it is processed by the agent.
Audit Metadata