The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from npm, which is a vendor-owned tool used for authentication and service interaction.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to execute various commands for connection management, data retrieval, and API proxying.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted message content retrieved from Microsoft Teams.
Ingestion points: list-channel-messages, list-chat-messages, and get-channel-message actions documented in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided.
Capability inventory: The skill has the ability to write to the platform via send-channel-message and the membrane request proxy as seen in SKILL.md.
Sanitization: No sanitization or validation of the ingested message content is described in the skill instructions.

microsoft-teams