The Agent Skills Directory

[SAFE]: The skill facilitates automation using the Rube MCP gateway (rube.app), which is a platform for integrating Composio toolkits with AI agents. No suspicious commands, obfuscation, or hidden behaviors were detected.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it instructs the agent to process and act upon data retrieved from external sources, such as tool discovery schemas and Echtpost API responses.
Ingestion points: Data returned by the RUBE_SEARCH_TOOLS and RUBE_MULTI_EXECUTE_TOOL functions as described in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or instructions to help the agent distinguish between tool-provided instructions and data content.
Capability inventory: The skill grants the agent the ability to discover tool schemas, manage connections, and execute remote tools through the MCP protocol.
Sanitization: No explicit sanitization or validation of the content returned from external tool calls is mentioned in the skill documentation.

echtpost-automation