admob-launchpad
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local scripts via
pnpm(pnpm console:open,pnpm eas:push). These scripts manage developer configuration and interact with the Expo Application Services (EAS) CLI to synchronize environment variables. - [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface (Category 8) through the ingestion of untrusted data from the user.
- Ingestion points: AdMob IDs provided by the user (e.g.,
EXPO_PUBLIC_ADMOB_ANDROID_APP_ID) are collected from chat or direct input. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within these IDs.
- Capability inventory: The skill has the ability to write to the local filesystem (
.env.local) and execute shell commands through thepnpm eas:pushworkflow, which targets theeasCLI. - Sanitization: The documentation does not describe any validation or sanitization procedures for the input strings before they are processed by the automated scripts.
Audit Metadata