cold-email-copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends adding an external tool via the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp. This connects the agent to an MCP server hosted on the author's official domain (manypi.com) to assist with email drafting and personalization research.- [INDIRECT_PROMPT_INJECTION]: The skill processes external information such as company hiring data, changelogs, and customer reviews to generate personalized email content. - Ingestion points: Data retrieved or provided by the user regarding target companies and leads (
SKILL.md). - Boundary markers: The instructions do not define specific delimiters to separate untrusted data from instructions.
- Capability inventory: The skill uses the ManyPI MCP toolset to generate text output.
- Sanitization: No automated sanitization of the input data is described within the skill instructions.
Audit Metadata