technical-buyer-outreach
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are purely advisory, focusing on communication styles and strategies for technical outreach, with no malicious code or prompt injection patterns identified.
- [EXTERNAL_DOWNLOADS]: The skill provides a command to register an Model Context Protocol (MCP) server:
https://mcp.manypi.com/mcp. This is a vendor-owned resource belonging to the author, manypicom, and is used for technographic research. - [INDIRECT_PROMPT_INJECTION]: The skill utilizes external technographic data (company tech stacks and public technical presence) via the ManyPI tool. This introduces a surface where untrusted data from the web could enter the agent's context. While the skill does not define specific sanitization or boundary markers for this data, the capability is standard for research tools.
Audit Metadata