Back to skill

Security audit

council-of-wisdom-omni

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed multi-agent decision helper with no executable code and only opt-in delegation to other workspace skills.

This appears appropriate to install if you want an advisory routing skill. Pay attention when it proposes using another workspace skill, especially for security, account, or high-impact tasks, and only approve delegation when the named downstream skill and reason make sense.

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.