ClawHub
Back to skill

Security audit

Common Ninja

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Common Ninja through OOMOL, but its first-time setup tells an agent to execute remote installer scripts directly in a shell.

Review this skill before installing. Its Common Ninja actions are clearly scoped and it asks for confirmation before changing or deleting widgets, but do not let an agent run the remote oo installer one-liners automatically; install the CLI through a verified/manual process and confirm any account connection or destructive Common Ninja action yourself.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remote script directly into a shell (curl ... | bash). This is a well-known unsafe pattern because it executes unaudited code fetched at runtime, and if the distribution server, network path, or script is compromised, arbitrary code execution occurs immediately on the host. In this skill context, the danger is increased because the content is operational guidance for an agent using shell access, so the instruction is more likely to be acted on automatically when oo is missing.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

Static analysis

No suspicious patterns detected.