Skills
skills/automateyournetwork/netclaw/msgraph-teams/Gen Agent Trust Hub

msgraph-teams

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the @anthropic-ai/microsoft-graph-mcp package from the npm registry using npx. Anthropic is a recognized trusted organization, and this package is the official implementation for Microsoft Graph integration.
  • [COMMAND_EXECUTION]: The skill uses npx and python3 to invoke the MCP server. This is the standard operational procedure for this type of integration and is used to perform legitimate tasks like sending channel messages and listing teams.
  • [SAFE]: The skill correctly handles sensitive Azure credentials by referencing environment variables rather than hardcoding secrets. No patterns for prompt injection, persistence, or data exfiltration to unknown domains were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 06:12 AM
Security Audit — agent-trust-hub — msgraph-teams