seo-vs-ads
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a required MCP connector from the developer's official domain (
https://connector.get-ryze.ai/mcp). This infrastructure is owned by the skill's author, ryze-ai-adgent, and is used to provide the necessary tool definitions for the marketing platform integrations. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external search marketing platforms which could contain untrusted user-generated search terms.
- Ingestion points: Search term data retrieved via
google_ads__runRawGaqland query data fromgoogle_search_console__runRawSearchAnalyticsare used in the analysis workflow. - Boundary markers: The workflow does not specify explicit delimiters for the external data.
- Capability inventory: The skill's capabilities are focused on data joining and table generation for reporting; it does not possess file-writing or system execution capabilities that could be exploited via malicious search terms.
- Sanitization: No specific sanitization or filtering of the search query data is mentioned in the prompt workflow.
Audit Metadata