ClawHub
Back to skill

Security audit

Skill Hub United

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed multi-hub skill installer; it has normal installer risks but no artifact-backed evidence of deception, exfiltration, or hidden behavior.

Install this only if you want an agent to fetch and install skills from the selected hub. Prefer trusted sources, read prompts carefully before choosing overwrite, and back up locally modified skills before replacing them.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The documented trigger phrases are broad enough to overlap with normal user requests like "install X" or "download X", which increases the chance an agent auto-invokes this skill without a clear confirmation boundary. In a skill that performs network fetches and filesystem writes, over-broad activation can lead to unintended package installation or replacement of local skill content.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README states that an existing target directory is wiped before extraction, but the warning about data loss is understated relative to the destructive behavior. If an agent or user selects overwrite/replace semantics accidentally, local modifications or manually installed files could be irreversibly deleted.

Static analysis

No suspicious patterns detected.