ClawHub
Back to skill

Security audit

Clawhub Skills Stats

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public ClawHub skill statistics and parses them locally, with no authentication, persistence, or file changes.

This is reasonable to install if you want quick ClawHub stats from the terminal. Use normal ClawHub slugs or URL-encoded search terms, and avoid pasting untrusted shell metacharacters into the placeholders.

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 (3)

External Script Fetching

High
Category
Supply Chain
Content
---
name: clawhub-skill-stats
description: "Query any ClawHub skill's statistics (stars, downloads, current installs, all-time installs) via curl and the public ClawHub API. Use when: user asks about a skill's popularity, stats, or metrics on ClawHub, wants to compare skill statistics, or needs to check how many stars/downloads/installs a ClawHub skill has — without opening the slow ClawHub web UI."
metadata:
  {
    "openclaw":
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

External Script Fetching

High
Category
Supply Chain
Content
```bash
for slug in "SLUG_1" "SLUG_2" "SLUG_3"; do
  curl -s "https://clawhub.ai/api/skill?slug=$slug" | python3 -c "
import sys, json
data = json.load(sys.stdin)
skill = data.get('skill', {})
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

External Script Fetching

High
Category
Supply Chain
Content
If the slug is unknown, search first:

```bash
curl -s "https://clawhub.ai/api/search?q=SEARCH_TERM" | python3 -c "
import sys, json
data = json.load(sys.stdin)
results = data.get('results', [])
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Static analysis

No suspicious patterns detected.