google-ads-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the 'google-ads-mcp' package directly from the author's GitHub repository using pip.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Google Ads API which can include attacker-controlled content in search terms or account history. \n1. Ingestion points: Google Ads API tool outputs (SKILL.md). \n2. Boundary markers: Write tools use a dry-run confirmation pattern ('confirm=False' by default). \n3. Capability inventory: Network access for API mutations and data retrieval across 29 tools. \n4. Sanitization: Write operations require explicit user approval via a confirmation flag to prevent accidental execution.
Audit Metadata