resend-integration-skills
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the official Resend MCP server implementation from GitHub (https://github.com/resend/mcp-send-email.git). This is an official source from a well-known email service provider.\n- [COMMAND_EXECUTION]: A provided setup script (scripts/setup-resend-mcp.sh) automates the installation process by executing commands for cloning the repository, installing dependencies with npm, and building the project.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the AI agent to read and process external data files (e.g., email.md, CSV customer lists) to perform email operations, which introduces a surface for indirect prompt injection.\n
- Ingestion points: Reads email templates from markdown files and recipient data from CSV/JSON files as described in the usage examples.\n
- Boundary markers: None identified in the provided prompt examples to distinguish between instructions and data.\n
- Capability inventory: The agent has the capability to send, schedule, and broadcast emails via the Resend tool.\n
- Sanitization: The skill documentation notes reliance on the Resend MCP server's internal validation mechanisms.
Audit Metadata