The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill relies on dynamic output from RUBE_SEARCH_TOOLS to determine execution plans and tool schemas. If the remote service provides malicious instructions within these schemas, the agent may execute unintended actions.
Ingestion points: RUBE_SEARCH_TOOLS response body.
Boundary markers: Absent; the agent is instructed to follow the execution plans returned by the tool.
Capability inventory: RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (can perform write operations in Rippling).
Sanitization: Absent; the skill directs the agent to use exact field names and types from search results.
External Dependency (LOW): The skill requires the addition of an external MCP server (https://rube.app/mcp) which is not on the trusted source list. This server acts as a proxy for sensitive Rippling data.

rippling-automation