microsoft-teams

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The Microsoft Teams integration skill provides actions and API proxy access to read chat messages, channel messages, and other communication data authored by external participants, presenting an indirect prompt injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to install and execute tooling from an unauthenticated, third-party npm package (@membranehq/cli) which constitutes a weak/unknown runtime external dependency.