microsoft-teams
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from Microsoft Teams, which constitutes a potential attack surface for indirect prompt injection where external content could influence agent behavior.
- Ingestion points: The agent is instructed to fetch data from channels, chats, and meeting transcripts using endpoints such as
GET /microsoft-teams/v1.0/teams/{team-id}/channels/{channel-id}/messagesandGET /microsoft-teams/v1.0/me/onlineMeetings/{meeting-id}/transcripts. - Boundary markers: The skill documentation does not provide specific instructions or delimiters to help the agent distinguish between its system instructions and the untrusted content retrieved from the API.
- Capability inventory: The skill includes high-impact capabilities such as sending messages, creating meetings, and deleting channels, which could be maliciously triggered if the agent follows instructions embedded in external data.
- Sanitization: No explicit mention of content filtering, sanitization, or validation of incoming API responses is included in the skill definition.
Audit Metadata