ClawHub
Back to skill

Security audit

ken-debt

Security checks for vulnerabilities and agentic risk

Overview

This skill only scans a project for disclosed ken: comments and reports them, with optional user-requested ledger output.

Before installing, expect the agent to read files in the active repository to find ken: comments. It should not modify anything unless you explicitly ask it to save the ledger.

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.