faceup-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill instructs users to add an external MCP server endpoint (https://rube.app/mcp). This domain is not identified as a trusted source, and the skill depends on this external service for its core logic.
  • [REMOTE_CODE_EXECUTION] (MEDIUM): The skill utilizes RUBE_REMOTE_WORKBENCH and RUBE_MULTI_EXECUTE_TOOL. These tools are designed to facilitate the execution of remote operations and workflows within the Composio ecosystem, creating a surface for remote command execution.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill dynamically ingests tool schemas and execution plans via RUBE_SEARCH_TOOLS, which are then used to guide the agent's tool execution. * Ingestion points: Results from RUBE_SEARCH_TOOLS (SKILL.md). * Boundary markers: Absent. * Capability inventory: Includes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (SKILL.md). * Sanitization: No evidence of schema validation or input sanitization before execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:44 PM