The Agent Skills Directory

[SAFE]: The skill does not contain any malicious code, prompt injections, or unauthorized data access patterns. It serves as a legitimate configuration for integrating Ragic with an AI agent.
[DATA_EXFILTRATION]: The skill facilitates data transfer between the agent and the Ragic platform via the Rube MCP server (rube.app). This interaction is the primary purpose of the skill and is protected by authenticated connection management through the RUBE_MANAGE_CONNECTIONS tool.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data from Ragic.
Ingestion points: Data retrieved from Ragic via RUBE_MULTI_EXECUTE_TOOL responses.
Boundary markers: Absent; the instructions do not define specific delimiters for tool outputs.
Capability inventory: The skill uses RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH which can perform database and automation tasks.
Sanitization: None specified; the skill relies on the underlying platform's safety guardrails to process tool outputs.

ragic-automation