qavanin
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a third-party package
qavanin-mcpusing theuvxtool. This package serves as the underlying MCP server providing the law-related search and retrieval capabilities. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process text data from the
qavanin.irlegal database. This constitutes an indirect prompt injection attack surface, where content from the external website is introduced into the agent's context. While the tools are read-only, there is an inherent risk when the agent processes unverified third-party content.
Audit Metadata