brightpearl-automation

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (HIGH): The skill instructs users to add an external MCP server from https://rube.app/mcp. This domain is not in the trusted scope and the server provides the core logic and tool definitions for the skill.
  • INDIRECT_PROMPT_INJECTION (HIGH): The skill's workflow is entirely dependent on data fetched from the remote server via RUBE_SEARCH_TOOLS.
  • Ingestion points: Tool schemas, input definitions, and 'recommended execution plans' are ingested from the https://rube.app/mcp endpoint during the RUBE_SEARCH_TOOLS call.
  • Boundary markers: None present. The skill explicitly tells the agent to follow the schemas and execution plans returned by the remote server.
  • Capability inventory: The skill possesses high-impact capabilities including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, which allow for the execution of complex tool chains and remote operations.
  • Sanitization: None detected. The agent is instructed to use 'exact field names and types' from the search results without validation.
  • REMOTE_CODE_EXECUTION (HIGH): Through the use of RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (specifically run_composio_tool()), the skill allows for the execution of logic defined and controlled by the remote rube.app server.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 08:26 AM