google-ads-landing-review
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data during its diagnostic workflow. 1. Ingestion points: Content from landing page URLs via
web_fetchandbrowser. 2. Boundary markers: Absent; the agent is not instructed to disregard potential instructions in fetched content. 3. Capability inventory: GAQL tool access, web fetching, and workspace file system writes. 4. Sanitization: Absent; external data is used directly to generate audits and drafts. - [EXTERNAL_DOWNLOADS]: The skill initiates network requests to retrieve landing page content from arbitrary external domains defined in the Google Ads account.
- [COMMAND_EXECUTION]: The skill executes Google Ads Query Language (GAQL) queries via an MCP tool to access campaign and performance metrics.
Audit Metadata