pp-google-ads

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs storing an OAuth2 access token via a direct CLI command (google-ads-pp-cli auth set-token YOUR_TOKEN_HERE) and supports profiles/sinks that can embed and transmit configuration values, which encourages passing secrets verbatim on the command line or into outputs/webhooks, creating an exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.80). The two go install repository URLs (go install github.com/mvanhorn/printing-press-library/library/marketing/google-ads/cmd/google-ads-pp-cli@latest and go install github.com/mvanhorn/printing-press-library/library/marketing/google-ads/cmd/google-ads-pp-mcp@latest) are presented as installation steps that fetch and compile/execute remote code and are required for the CLI/MCP to run, so they represent runtime external dependencies that execute remote code.

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

• Direct money access detected (high risk: 1.00). The skill explicitly exposes Google Ads billing and budget management APIs that can modify ad spend and billing state. Examples in the prompt include commands that "create, update, or remove" campaign budgets (customers_campaign_budgets), create/cancel billing setups (customers_billing_setups), create/update/remove account budget proposals (customers_account_budget_proposals), and access payments/accounts and invoices (customers_payments_accounts, customers_invoices). Because it can programmatically change budgets and billing configurations (i.e., directly affect ad spend and billing), it constitutes direct financial execution capability.