ClawHub
Back to skill

Security audit

qa-engineer-assistant

Security checks across malware telemetry and agentic risk

Overview

This QA testing helper is coherent and purpose-aligned, but users should treat its generated API tests as real network code and handle test credentials carefully.

Install is reasonable for QA workflows. Before running generated API tests, replace sample credentials with dedicated low-privilege test accounts or CI secrets, avoid production targets unless explicitly intended, and avoid logging full responses when they may contain tokens, cookies, passwords, or personal data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the model to load local reference files and use a script to generate API test boilerplate, which implies file access and code/tool capability usage, yet no permissions are declared. This creates a transparency and policy-enforcement gap: the runtime may allow file/network-capable behavior without users or platform controls having an explicit declaration to review or constrain.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The guide includes hard-coded example credentials and shows them being transmitted to a remote login endpoint. Even if presented as sample code, embedding reusable-looking credentials in a QA skill can normalize unsafe practices, lead users to copy them into real environments, and cause accidental credential exposure over networks or into logs and version control.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The generator creates a conftest.py that will automatically perform a real login request using user-supplied credentials when tests run. In a QA assistant context this is risky because users may replace the placeholders with real test or even production credentials and unknowingly transmit secrets to a live endpoint without an explicit safety warning, environment gating, or dry-run control.

External Transmission

Medium
Category
Data Exfiltration
Content
@pytest.fixture(scope="session")
def auth_token(base_url):
    """登录获取 token，整个测试会话只执行一次"""
    resp = requests.post(f"{base_url}/auth/login", json={
        "username": "test@example.com",
        "password": "Test@1234"
    })
Confidence
90% confidence
Finding
requests.post(f"{base_url}/auth/login", json=

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.