The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires adding an external Model Context Protocol (MCP) server endpoint at https://rube.app/mcp. This server provides the tool definitions and capabilities for the agent.\n- [DATA_EXFILTRATION]: The skill facilitates the connection of a Datadog account to the rube.app third-party service. This grants the service access to potentially sensitive operational data, including logs and infrastructure details.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through data ingested from Datadog.\n
Ingestion points: DATADOG_SEARCH_LOGS and DATADOG_LIST_EVENTS pull arbitrary strings from Datadog into the agent context.\n
Boundary markers: There are no boundary markers or instructions to disregard potential commands found within the retrieved data.\n
Capability inventory: The agent has access to destructive or modifying tools like DATADOG_DELETE_DASHBOARD, DATADOG_UPDATE_DASHBOARD, and DATADOG_CREATE_MONITOR.\n
Sanitization: The skill does not implement or recommend sanitization for incoming data before it is used to drive agent behavior.

datadog-automation