boloforms-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill requires the configuration of an external MCP server at https://rube.app/mcp. This domain and its associated services (Composio) are not on the trusted sources list, meaning the integrity of the tools and instructions provided cannot be statically verified.
  • COMMAND_EXECUTION (MEDIUM): The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform actions. These tools execute logic on remote environments based on schemas discovered at runtime from the external server, which could lead to unauthorized actions if the external source is compromised.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it dynamically fetches tool schemas and instructions.
  • Ingestion points: Data returned from the RUBE_SEARCH_TOOLS call via the rube.app endpoint.
  • Boundary markers: Absent. The instructions tell the agent to 'Always search tools first' and follow the returned schemas without validation.
  • Capability inventory: Remote tool execution, connection management, and workbench operations across multiple tools.
  • Sanitization: None detected. The skill assumes the validity of the external search results.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:38 PM