skills/alinaqi/maggy/ms-teams-apps/Gen Agent Trust Hub

ms-teams-apps

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and provides instructions for installing official packages and CLI tools from Microsoft and Anthropic. These include @microsoft/teams.cli, @microsoft/teams.ai, and @anthropic-ai/sdk.\n- [COMMAND_EXECUTION]: Contains standard shell commands for development workflows, including project initialization via npx, resource provisioning with az CLI, and deployment using teamsfx.\n- [INDIRECT_PROMPT_INJECTION]: The provided code templates establish an architecture where user messages are passed directly to large language models. While typical for conversational agents, this design creates an inherent surface for indirect prompt injection which should be managed by the developer during implementation.\n- [SAFE]: No malicious obfuscation, persistence mechanisms, or unauthorized data exfiltration patterns were detected. All external resources and domains belong to well-known technology providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:45 PM
Security Audit — agent-trust-hub — ms-teams-apps