executive-outreach-register
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a command to add a Model Context Protocol (MCP) server to the agent environment (
claude mcp add). This allows the agent to interact with an external research tool provided by the author. - [EXTERNAL_DOWNLOADS]: The skill references a remote endpoint (
https://mcp.manypi.com/mcp) to enable research functionality. This resource is associated with the skill's author and serves the primary purpose of gathering business context for outreach. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process company situation data and executive priorities. 1. Ingestion points: Business research and public statements from target companies. 2. Boundary markers: Absent. 3. Capability inventory: Tool execution via the integrated ManyPI MCP server. 4. Sanitization: Absent. While this represents an attack surface for external data to influence the agent, the risk is inherent to the specific research task and is managed by standard agent guardrails.
Audit Metadata