The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the hermes command-line tool for all meeting pipeline operations, including validation, inspection, and job re-runs. This is a standard way to interface with the specified Microsoft Graph service.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process Microsoft Teams meeting transcripts, which are external data sources that could contain malicious instructions designed to influence the agent's behavior. * Ingestion points: Meeting transcripts and transcript artifacts resolved via Microsoft Graph API calls, as described in the fetch and run subcommands (SKILL.md). * Boundary markers: The instructions do not specify any delimiters or special handling to isolate the meeting content from the agent's primary instructions. * Capability inventory: The hermes teams-pipeline CLI has capabilities for network communication with Microsoft Graph, managing webhook subscriptions, and inspecting stored meeting jobs. * Sanitization: There are no mentions of sanitizing, filtering, or validating the meeting transcripts before the agent processes them for summarization.

teams-meeting-pipeline