pp-google-ads

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill operates a Google Ads CLI that queries campaigns, ad groups, and customer reports where third-party ad content, keywords, or customer data can be ingested and exposed to prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install an external CLI and Go module from GitHub (github.com/mvanhorn/printing-press-library/...), which is an unofficial third-party repository providing executable runtime code.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill provides a CLI interface for the Google Ads API (google-ads-pp-cli). It includes tools for managing campaigns, budgets, ad groups, and billing operations (such as creating/canceling billing setups via customers-billing-setups and account budget proposals via customers-account-budget-proposals). Managing budgets and billing setups in an advertising platform constitutes Direct Financial Execution Authority (modifying advertising budgets and financial account setups).