The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external MCP server endpoint (https://rube.app/mcp) and documentation from composio.dev. These are well-known technology services for AI tool orchestration and do not represent a security risk.
[DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. The skill uses RUBE_MANAGE_CONNECTIONS for authenticated access to Ninox, which is standard for this type of integration.
[PROMPT_INJECTION]: The skill utilizes a dynamic tool discovery mechanism where tool schemas are fetched at runtime.
Ingestion points: RUBE_SEARCH_TOOLS responses are incorporated into the agent's context (SKILL.md).
Boundary markers: None explicitly defined in the prompt instructions.
Capability inventory: The skill allows execution of discovered tools via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (SKILL.md).
Sanitization: No specific sanitization or validation of the returned schemas is documented within the skill file.

ninox-automation