monetization-sdk-integration
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted data such as SDK names, GitHub URLs, and Pull Request (PR) diffs during the pre-integration and audit phases. This creates a surface where malicious instructions embedded in the external data could influence the agent's behavior.
- Ingestion points: The "Pre-integration checklist" inputs (SDK name, GitHub URL) and PR diffs during the build-time audit.
- Boundary markers: The skill does not define specific delimiters or instructions to treat the checklist data or PR diffs as untrusted content.
- Capability inventory: The skill uses
ripgrep(rg) for auditing. While this skill focuses on auditing, the agent environment may have broader capabilities such as file modification (PrivacyInfo.xcprivacy,Package.swift) or PR management. - Sanitization: No data validation or sanitization steps are provided for the information gathered in the pre-integration checklist.
- [EXTERNAL_DOWNLOADS]: The skill references the official Google Mobile Ads SDK (
swift-package-manager-google-mobile-ads). This is a legitimate dependency from a well-known service provider for the intended purpose of monetization. - [COMMAND_EXECUTION]: The skill provides a
ripgrep(rg) command for developers or agents to audit the source code for unauthorized import statements. This is a diagnostic read-only operation intended to enforce the isolation contract.
Audit Metadata