skills/microsoft/teams-sdk/teams-dev/Gen Agent Trust Hub

teams-dev

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Command Execution]: The skill utilizes the teams Developer CLI and the Azure (az) CLI to manage application infrastructure, register bots, and configure authentication. These operations are standard for Microsoft Teams development workflows.
  • [External Package Installation]: The skill guides the user to install the @microsoft/teams.cli package globally via npm. This is the official developer tool provided by the vendor for managing Teams applications.
  • [Credential Management]: The guide instructs the agent to write sensitive information (Client ID, Client Secret, Tenant ID) into .env or appsettings.json files. This is a standard practice for local development environment configuration.
  • [Indirect Prompt Injection Surface]: The Slack Bolt Migration guide involves the agent reading and processing user-provided Slack application source code and manifests to port them to the Teams SDK. While this presents an ingestion point for untrusted data, the skill is designed to facilitate developer tasks and the risk is considered low within this context.
  • Ingestion points: The agent reads Slack source code and manifest files provided by the user in the references/guide-migrate-slack-bolt.md workflow.
  • Boundary markers: Explicit boundary markers are not defined within the instruction files themselves.
  • Capability inventory: The skill possesses the ability to execute shell commands via teams and az CLIs, perform project scaffolding (teams project new), and write files to the local system.
  • Sanitization: The instructions do not specify explicit sanitization steps for the ingested code, relying on the underlying model's logic during the migration process.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 03:45 AM