ClawHub
Back to skill

Security audit

question-bank-api

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed question-bank API helper that uses a user-supplied API key and network calls for its stated education-data purpose.

Install only if you intend to use the 学库宝 question-bank API. Keep QB_API_BASE at the official HTTPS provider URL unless you explicitly trust another gateway, protect QB_API_KEY like a password, and choose Word export filenames carefully to avoid overwriting existing files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tainted flow: 'req' from os.environ.get (line 54, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
last = None
    for attempt in range(3):
        try:
            with urllib.request.urlopen(req, timeout=timeout) as r:
                if raw or out_path:
                    data = r.read()
                    if out_path:
Confidence
89% confidence
Finding
with urllib.request.urlopen(req, timeout=timeout) as r:

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill explicitly instructs use of environment variables for API credentials and directs a script to make outbound network requests, but no declared permissions are present. That creates a transparency and policy-enforcement gap: an agent or reviewer may not realize the skill can access secrets and external services, increasing the chance of unintended credential use or data exfiltration through the third-party API.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The skill says exported Word files are written to the working directory, but does not clearly warn about local file creation or overwrite behavior. If output paths are predictable or user-controlled, this can lead to accidental overwrites of existing files, leakage of generated educational content into shared workspaces, or confusion about where artifacts are stored.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.