Back to skill

Security audit

Coordinator (EN)

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only coordinator skill that transparently tells an agent to gather and summarize other agents' reports.

This skill appears safe to install if you want an agent to coordinate and summarize outputs from other agents. The main practical consideration is data handling: because it aggregates reports, only use it with agents and tasks where sharing that combined information with the coordinator and CEO-style recipient is acceptable.

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.