linkedin-automation

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard set of workflows for LinkedIn automation via a third-party MCP provider (Rube). It appropriately uses the Rube MCP server (https://rube.app/mcp) for executing LinkedIn-related tasks.
  • [SAFE]: Authentication is handled through a structured connection management system (RUBE_MANAGE_CONNECTIONS) that utilizes standard LinkedIn OAuth. No hardcoded credentials or unsafe secret management practices were found.
  • [SAFE]: No obfuscation techniques, remote code execution patterns, or privilege escalation attempts were detected in the skill instructions or metadata.
  • [SAFE]: The skill maintains clear boundaries by requiring an explicit search for tool schemas (RUBE_SEARCH_TOOLS) before execution, which is a best practice for dynamic MCP environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 01:00 AM
Security Audit — agent-trust-hub — linkedin-automation