The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or security violations were detected. The skill follows standard procedures for tool-calling AI agents.- [EXTERNAL_DOWNLOADS]: The skill connects to an external MCP server at https://rube.app/mcp and refers to documentation at https://composio.dev/toolkits/tisane. These are legitimate endpoints for the Composio platform used for the skill's primary purpose.- [COMMAND_EXECUTION]: The skill utilizes MCP-specific tools like RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform Tisane operations. These are standard tool-calling actions and do not involve unauthorized command execution.- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection surface as it processes responses from external tools to determine future steps.
Ingestion points: External data enters via RUBE_SEARCH_TOOLS and RUBE_MULTI_EXECUTE_TOOL in SKILL.md.
Boundary markers: No explicit markers are present to delimit external data.
Capability inventory: The skill can execute various Tisane tools via RUBE_MULTI_EXECUTE_TOOL in SKILL.md.
Sanitization: No explicit sanitization or validation of tool output is described.

tisane-automation