ClawHub
Back to skill

Security audit

u2-downloader

Security checks for vulnerabilities and agentic risk

Overview

This is a simple YouTube downloader wrapper for a third-party API, with no hidden code or destructive behavior, but users should know their API key and video URLs go to that service.

Install only if you trust u2foru.site to process your YouTube URLs and service API key. Use a dedicated key if possible, review the service's terms and privacy practices, and consider whether downloading a given video complies with applicable platform rules and law.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs users to obtain and provide an API key for a third-party service and to submit YouTube URLs to that same service, but it does not clearly warn that both credentials and requested content are transmitted off-platform. This creates a meaningful privacy and trust risk because users may assume the skill operates locally or within OpenClaw rather than disclosing data to an external operator.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The curl example demonstrates the same external transmission pattern: a bearer API key and requested video URL are sent to https://u2foru.site. While expected for a downloader service, it is still a valid vulnerability finding in skill-review context because the skill encourages secret submission and third-party processing without adequate warning or trust documentation.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

bash
# Download a video
curl -X POST https://u2foru.site/api/v1/skill/download \
  -H "Authorization: Bearer sk-yt-xxxxx" \
  -H "Content-Type: application/json" \
  -d '{"youtube_url": "https://youtube.com/watch?v=dQw4w9WgXcQ", "resolution": "720"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The example code sends an Authorization bearer token and user-supplied YouTube URL to an external domain, confirming real external data transmission. In the context of an agent skill, this is security-relevant because it operationalizes credential sharing with a third party and content disclosure without accompanying consent, minimization, or handling guarantees.

Content

Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.

md
BASE_URL = "https://u2foru.site"

# Download
resp = requests.post(
    f"{BASE_URL}/api/v1/skill/download",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"youtube_url": "https://youtube.com/watch?v=dQw4w9WgXcQ", "resolution": "720"}

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The quick-install instructions present the command exclusively in Chinese ("帮我安装这个 skill…") and do not indicate that other languages are supported. This can violate language/locale policy when a specific language is imposed without opt-in or alternative phrasing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.