sendgrid-automation
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, code obfuscation, or persistence mechanisms were detected.
- [EXTERNAL_DOWNLOADS]: The skill references the Rube MCP server at https://rube.app/mcp for tool access.
- [DATA_EXFILTRATION]: No unauthorized access to sensitive local files or credentials was found; authentication is handled via the Rube connection management tools.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it handles external data for emails and contacts. Ingestion points: email content fields and contact data described in SKILL.md. Boundary markers: Absent. Capability inventory: marketing campaign delivery and contact management. Sanitization: Not explicitly defined in the skill; deferred to the underlying SendGrid API and Rube MCP service layers.
Audit Metadata