ClawHub
Back to skill

Security audit

全球航班查询与预订

Security checks across malware telemetry and agentic risk

Overview

This travel assistant is coherent with its stated purpose, but flight, hotel, and currency lookups send query details to external services.

Install only if you are comfortable sending travel-search details such as routes, dates, flight numbers, hotel IDs, and currency pairs to the skill's cloud proxy or public exchange-rate API. Avoid using it for sensitive or confidential itineraries, and be cautious about overriding RG_PROXY or PROXY_TOKEN unless you control the endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tainted flow: 'req' from os.environ.get (line 25, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
method="POST",
    )
    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            data = json.loads(resp.read().decode("utf-8"))
            return data
    except urllib.error.HTTPError as e:
Confidence
94% confidence
Finding
with urllib.request.urlopen(req, timeout=30) as resp:

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill advertises networked/cloud-backed capabilities in the documentation but does not declare corresponding permissions, creating a transparency and governance gap. This can mislead users or platform reviewers about what data leaves the local environment and weakens enforcement of least-privilege controls.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill states that flight, hotel, and exchange-rate queries use a cloud proxy/public API, but the user-facing description does not clearly warn that travel search data will be sent off-platform. Users may disclose itineraries, locations, and travel timing without informed consent, which creates privacy and profiling risks.

Missing User Warnings

Medium
Confidence
81% confidence
Finding
The skill forwards user-supplied flight and hotel search data to an external proxy service without any clear user-facing notice or consent mechanism. Travel searches can expose itinerary intent, destinations, dates, and potentially sensitive personal context, so undisclosed transmission is a privacy issue even if the remote service is legitimate.

Missing User Warnings

Low
Confidence
69% confidence
Finding
The exchange-rate tool sends requested currency pair information to a third-party API without telling the user. The data is not highly sensitive in isolation, but it is still an external disclosure and should be documented, especially in a travel assistant that aggregates multiple personal trip details.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
import urllib.error

PROXY_URL = os.environ.get("RG_PROXY", "https://1439498936-460a7b6oqn.ap-guangzhou.tencentscf.com")
PROXY_TOKEN = os.environ.get("PROXY_TOKEN", "tp_8k2mX9vQ4z")

# ============================================================
# 第一组：RG代理工具 (5个)
Confidence
98% confidence
Finding
os.environ.get("PROXY_TOKEN

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.