keyword-research
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides setup instructions for adding an external MCP server via the URL
https://connector.get-ryze.ai/mcp. This is the vendor's infrastructure required for the skill's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill represents a data ingestion surface as it processes external data from Google Ads API, Google Search Console, and DataForSEO endpoints.
- Ingestion points: Data enters through tool outputs from
google_ads__generateKeywordIdeas,google_ads__generateKeywordHistoricalMetrics, andgoogle_search_console__runRawSearchAnalytics. - Boundary markers: No specific boundary markers or 'ignore' instructions are used when interpolating this external data into the agent context.
- Capability inventory: The skill is limited to reading data and formatting it into reports and tables; it does not possess file-write, network-send (beyond the MCP calls), or execution capabilities.
- Sanitization: No explicit sanitization or filtering of the API-returned text is performed before it is processed by the LLM.
Audit Metadata