m365-agents-dotnet
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's required workflow accepts and processes arbitrary user-generated activity text via the /api/messages endpoint (AgentApplication routing -> adapter.ProcessAsync) and handles OnMessageAsync (reading turnContext.Activity.Text), and also consumes activity streams from CopilotClient.StartConversationAsync/AskQuestionAsync, so untrusted third-party/user content is ingested and can influence agent behavior.
Audit Metadata