ai-visibility
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add the Ryze MCP connector from 'https://connector.get-ryze.ai/mcp'. This is a vendor-managed resource provided for the skill's stated analytical functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Google Analytics, Search Console, and external landing pages, creating a potential surface for indirect prompt injection.
- Ingestion points: Data enters the context through 'google_analytics__' and 'google_search_console__' tool outputs, and by fetching the content of top cited landing pages (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or ignore-instructions to isolate untrusted web content from the agent's logic.
- Capability inventory: The skill utilizes analytics data retrieval and web page fetching tools.
- Sanitization: There is no evidence of filtering or sanitization applied to the data retrieved from external analytics sources or web pages.
Audit Metadata