The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @useclawlink/cli package from the NPM registry. This package is provided by the skill's author (clawlink-hq).
[COMMAND_EXECUTION]: The skill relies on shell commands to interact with the ClawLink CLI for user authentication, action discovery, and execution within the Microsoft Teams environment.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from external sources (Microsoft Teams chats and messages).
Ingestion points: Data is ingested via microsoft_teams_list_user_chat_messages and microsoft_teams_chats_get_all_chats as defined in SKILL.md.
Boundary markers: The instructions recommend that the agent reads data before performing writes and seeks user confirmation, but it does not specify technical delimiters or boundary markers for the ingested content itself.
Capability inventory: The skill possesses write capabilities, such as microsoft_teams_create_meeting, which are executed through the CLI.
Sanitization: There is no mention of sanitization, filtering, or escaping of the chat content retrieved from the external service.

microsoft-teams