mailboxlayer-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Dynamic Execution (MEDIUM): The skill uses RUBE_SEARCH_TOOLS to fetch schemas and RUBE_MULTI_EXECUTE_TOOL to execute them. This runtime discovery pattern allows agent behavior to be influenced by external data.
  • External Reference (MEDIUM): The skill directs users to add https://rube.app/mcp as an MCP server. This domain is not on the trusted list for dependencies.
  • Indirect Prompt Injection (LOW): The skill ingests untrusted metadata from the RUBE_SEARCH_TOOLS tool. 1. Ingestion points: RUBE_SEARCH_TOOLS response; 2. Boundary markers: Absent; 3. Capability inventory: RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH; 4. Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:42 PM