teams-meeting-pipeline
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
hermesCLI tool to perform all operational tasks. It uses varioushermes teams-pipelinesubcommands to validate configurations, inspect job statuses, and manage Microsoft Graph webhook subscriptions. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it is designed to ingest and process external meeting transcripts and metadata.
- Ingestion points: Meeting transcripts and job metadata are retrieved via
hermes teams-pipeline fetchandhermes teams-pipeline run(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the meeting data it processes.
- Capability inventory: The agent has the ability to execute terminal commands via the
hermesCLI (SKILL.md). - Sanitization: There are no documented steps for sanitizing or validating the content of meeting transcripts before they are processed for summaries or action items.
Audit Metadata