crm-data-hygiene
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides utility command templates using standard tools (tr, awk, sed, grep) to process local files such as
emails.txtandleads.csvfor normalization and deduplication purposes. - [EXTERNAL_DOWNLOADS]: The skill includes instructions to add an MCP (Model Context Protocol) server from
https://mcp.manypi.com/mcp. This is a vendor-owned resource used to extend the skill's capabilities. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external CRM data, which constitutes an ingestion point for untrusted content. However, the skill includes extensive normalization, validation, and render-testing instructions that serve as effective sanitization and human-in-the-loop review layers.
Audit Metadata