dental-medical-practice-leads
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to add a Model Context Protocol (MCP) server from
https://mcp.manypi.com/mcp. This is the official infrastructure of the skill's author, ManyPI, and is necessary for the intended functionality of lead discovery and qualification. - [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data from external, untrusted sources such as dental practice websites, regulatory registers, and review platforms. This creates a surface for indirect prompt injection if those external sites contain malicious instructions designed to influence the agent's behavior during data extraction.
- Ingestion points: Team pages, contact pages, regulatory registers, and review sites mentioned in SKILL.md.
- Boundary markers: None specified in the instructions for data parsing.
- Capability inventory: The agent uses the ManyPI MCP tool to query and retrieve practice data, potentially involving web scraping capabilities.
- Sanitization: No explicit sanitization or validation of the retrieved web content is described.
Audit Metadata