ClawHub
Back to skill

Security audit

ken-gain

Security checks for vulnerabilities and agentic risk

Overview

This skill only displays measured Ken benchmark results and explicitly avoids edits, persistence, or invented claims.

Before installing, understand that this skill is informational: it should show only existing Ken benchmark medians or an empty state, and it should not modify files or claim live per-repository savings.

SkillSpector

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.