9router-web-search
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation references a configuration file hosted on the author's official GitHub repository (decolua/9router).
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from external search engines and social media, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is ingested through search result snippets, article content, and public social media posts retrieved from providers like Tavily, Brave, and Xquik via the 9Router API.
- Boundary markers: The provided documentation does not specify explicit boundary markers or delimiters for the external content.
- Capability inventory: The skill facilitates network requests to the 9Router endpoint and retrieves structured data to be processed by the agent.
- Sanitization: The skill instructions do not outline specific validation, filtering, or escaping mechanisms for content retrieved from external search providers.
Audit Metadata