Back to skill

Security audit

Kamis Cli

Security checks for vulnerabilities and agentic risk

Overview

The artifact appears to be legitimate ClawHub development and maintainer tooling, with powerful actions disclosed and gated rather than hidden.

Install or use this only in a trusted ClawHub maintainer/development context. Be careful with commands that touch GitHub, Convex, or ClawHub moderation state, and confirm targets before actions such as bans, role changes, publishing, or full-access review helpers.

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.