ClawHub
Back to skill

Security audit

clawteam-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed multi-agent orchestration guide, but it should be used carefully because it can spawn local agents and modify worktrees through an external CLI.

Install only if you intentionally want local multi-agent orchestration. Verify and pin the external `clawteam` CLI, start in a disposable repository, keep approval prompts enabled, avoid subprocess/custom backend modes unless you trust the environment, monitor spawned agents, and clean up `~/.clawteam/` state and worktrees when finished.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger list includes very broad terms such as "team," "swarm," and "parallel agents," which are common in benign conversation and can cause the skill to activate unintentionally. Because this skill can create agent swarms, launch subprocess-backed workers, and operate on repositories/worktrees, accidental invocation increases the chance of unintended high-impact actions.

Static analysis

No suspicious patterns detected.