ClawHub
Back to skill

Security audit

Skill Lookup

Security checks for vulnerabilities and agentic risk

Overview

This skill appears legitimate, but it needs review because broad prompts can lead it to install third-party skills globally while skipping confirmation.

Install only if you want an agent helper for explicit skill discovery. Before allowing it to install anything, inspect the recommended skill source and run installs only after clear confirmation, preferably without `-g` or `-y` unless you intentionally want a global install.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The top-level description triggers on very common phrases like 'how do I do X' and general interest in extending capabilities, which makes the skill eligible in many ordinary conversations. Because this skill can progress to recommending and installing third-party packages, overly broad activation increases the chance of unnecessary or unintended package discovery and supply-chain exposure.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation conditions are broad and ambiguous, covering generalized capability questions and vague expressions of needing help in a domain. In context, this can route routine assistance requests into a workflow that searches for external skills and may culminate in installation, increasing the risk of unnecessary third-party dependency introduction.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs the agent to install skills using a global flag and skip-confirmation flag, which enables system-impacting changes without an interactive safeguard. Since skills may come from GitHub or other external sources, this creates a meaningful supply-chain and persistence risk if a malicious or inappropriate package is selected or if the user did not fully understand the effect of the command.

Static analysis

No suspicious patterns detected.