google-ads-connect
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs standard authentication and configuration tasks for Google Ads integration. It provides clear diagnostic steps for managing environment variables like GOOGLE_APPLICATION_CREDENTIALS and GOOGLE_ADS_DEVELOPER_TOKEN without exposing sensitive data.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from the Google Ads API. 1. Ingestion points: Account names, IDs, and campaign metadata retrieved via the google-ads-mcp tool as described in SKILL.md. 2. Boundary markers: The data is presented to the operator in markdown tables; no explicit 'ignore instructions' delimiters are used. 3. Capability inventory: The skill can invoke MCP tools and write to the workspace file workspace/ads/account.md. 4. Sanitization: No specific filtering or escaping of API-provided strings is detailed in the instructions.
Audit Metadata