ClawHub

X Deep Miner

Security checks across malware telemetry and agentic risk

Overview

This skill is an incomplete, local X-to-Obsidian archiving scaffold with user-directed browser and cron steps, not evidence of hidden exfiltration or destructive behavior.

Install only if you are comfortable with a tool that may use your logged-in X browser profile and save collected content locally. Before adding the hourly cron job, confirm the output directory, retention expectations, and any X/Twitter policy or privacy constraints.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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 (4)

Tainted flow: 'CONFIG_FILE' from os.environ.get (line 20, credential/environment) → open (file write)

Medium
Category
Data Flow
Content
def save_config(config: dict):
    """保存配置"""
    CONFIG_FILE.parent.mkdir(parents=True, exist_ok=True)
    with open(CONFIG_FILE, 'w') as f:
        json.dump(config, f, indent=2)
Confidence
87% confidence
Finding
with open(CONFIG_FILE, 'w') as f:

Tainted flow: 'output_path' from os.environ.get (line 168, credential/environment) → open (file write)

Medium
Category
Data Flow
Content
filename = f"{datetime.now().strftime('%Y%m%d_%H%M%S')}_{safe_title}.md"
    
    output_path = OUTPUT_DIR / category / filename
    with open(output_path, 'w', encoding='utf-8') as f:
        f.write(note)
    
    print(f"  ✓ 已保存: {output_path}")
Confidence
91% confidence
Finding
with open(output_path, 'w', encoding='utf-8') as f:

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The description promotes hourly automated scanning, translation, and archiving of X/Twitter content but omits warnings about continuous collection, storage, and possible policy or privacy implications. This lack of disclosure can mislead users about ongoing monitoring behavior and the volume of third-party content being retained.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill frames Chinese translation as a mandatory behavior rather than a user-selectable option. While not directly enabling code execution, it removes user agency and can cause unintended processing, storage, or redistribution of transformed content in a form the user did not request.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal