warm-intro-request-outreach
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests adding an MCP (Model Context Protocol) server from
https://mcp.manypi.com/mcp. This server provides the account research and data enrichment functionality described. The domain is associated with the skill author,manypicom, representing a standard integration of the vendor's own services. - [INDIRECT_PROMPT_INJECTION]: The skill handles prospecting data and connection information from external sources (target accounts, social connection data), which presents a theoretical attack surface for indirect prompt injection.
- Ingestion points: Target account details, contact names, and connection data retrieved or cross-referenced by the MCP tool in
SKILL.md. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill leverages an MCP tool (
manypi) for network mapping and account enrichment. - Sanitization: No specific sanitization or filtering logic is described for the external data ingested.
Audit Metadata