Build Teams.ai Apps with Anthropic Claude

• Outcome: Pass
• Latest audit: May 28, 2026 at 1:45 AM UTC
• Version:
  1.1.0

Overview

This is a coherent developer setup guide for adding Claude and optional You.com web tools to a Teams.ai app, with expected external-service and API-key considerations.

Install only if your organization permits Teams app messages, search queries, URLs, and retrieved web content to be processed by Anthropic and You.com. Keep API keys out of source control, pin package versions with a lockfile, and consider scoping or disabling You.com MCP tools for sensitive internal Teams environments; You.com documents tool scoping options for the MCP server. ([you.com](https://you.com/docs/build-with-agents/mcp-server))

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly encourages web search and content extraction but does not warn that user prompts, search queries, URLs, and fetched page content may be transmitted to external services (Anthropic and You.com). In an enterprise Teams context, users may unknowingly send sensitive internal data or private links to third-party systems, creating a real data exposure risk.

VirusTotal

66/66 vendors flagged this skill as clean.