tmeet-skill

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow includes real-time event streaming via tmeet event consume, which monitors and consumes external message feeds containing outsider-authored free text from meeting events.

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 an npm package (@tencentcloud/tmeet@latest) from a registry URL/locator, which constitutes an operational runtime dependency.