emaillistverify-automation

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (HIGH): The skill instructs the user to configure an untrusted MCP server at https://rube.app/mcp. This domain is not among the Trusted External Sources, and connecting to it allows the external server to provide and execute tools within the agent context.
  • REMOTE_CODE_EXECUTION (HIGH): The tools RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH facilitate the execution of remote logic or tools defined by the untrusted Rube MCP server, constituting a remote code execution risk.
  • DATA_EXFILTRATION (MEDIUM): Sensitive information such as email lists are processed through the rube.app proxy to reach the Emaillistverify service, exposing private user data to an unverified third party.
  • PROMPT_INJECTION (HIGH): The skill possesses a high-severity indirect prompt injection surface. Ingestion points: Emaillistverify data enters the agent context via Rube tools. Boundary markers: None mentioned in the instructions. Capability inventory: RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (file/tool execution). Sanitization: None described. This allows malicious content within processed emails to potentially trigger unauthorized tool executions or exfiltrate data.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 12:23 AM