web-intelligence-router
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implementation is a standard wrapper for internal web intelligence tools. No malicious patterns were detected in the routing logic or metadata.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of external web content, which presents an inherent surface for indirect prompt injection where malicious instructions could be embedded in the searched or crawled websites. 1. Ingestion points: router.py via WebIntelligenceRouter (external web content). 2. Boundary markers: Not explicitly defined in the provided script, relying on the underlying router implementation. 3. Capability inventory: Web search, extraction, operation, and crawling capabilities are present. 4. Sanitization: Employs WebRouterInput.model_validate for input data structure validation.
Audit Metadata