m365-teams

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references @pnp/cli-microsoft365, a well-known community command-line tool for Microsoft 365 environments.
  • [COMMAND_EXECUTION]: Executes administrative tasks and messaging operations using the m365 CLI via the Bash tool.
  • [PROMPT_INJECTION]: The skill ingests data from external sources such as Teams messages and meeting transcripts, presenting an attack surface for indirect prompt injection.
  • Ingestion points: Fetches untrusted content using m365 teams message list, m365 teams chat message list, and m365 teams meeting transcript list.
  • Boundary markers: The instructions lack delimiters or specific directives to help the agent distinguish between its instructions and content from message bodies.
  • Capability inventory: The agent has Bash access to perform administrative actions like channel removal, message sending, and app management.
  • Sanitization: There are no documented procedures for sanitizing or escaping the content retrieved from external messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:24 AM
Security Audit — agent-trust-hub — m365-teams