The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on shell commands using npx to interact with the ClawLink service and perform Microsoft Teams actions.
[EXTERNAL_DOWNLOADS]: Downloads and executes the @useclawlink/cli package from the NPM registry via npx during setup and operation.
[CREDENTIALS_UNSAFE]: The skill manages authentication data stored in the local file system at ~/.clawlink/credentials.json.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Microsoft Teams, creating a surface for potential injection attacks.
Ingestion points: External data enters the context through actions like microsoft_teams_list_user_chat_messages and microsoft_teams_get_chat as described in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers are defined for the ingested chat data, although a manual confirmation step is recommended for write operations.
Capability inventory: The agent can perform write operations, such as creating meetings and executing other Teams actions, via the npx @useclawlink/cli run command.
Sanitization: There is no evidence of sanitization or filtering applied to the external content retrieved from Teams.

microsoft-teams