ClawHub
Back to skill

Security audit

机票比价

Security checks across malware telemetry and agentic risk

Overview

The skill coherently performs flight price comparison, but it sends travel search details through a disclosed cloud proxy and includes a proxy token in source code.

Install only if you are comfortable with your flight route and date being sent to the publisher's Tencent Cloud proxy and onward to travel platforms. The skill does not book tickets or modify accounts, but the embedded proxy token and third-party data flow are worth reviewing if you require strict privacy or enterprise credential handling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly routes user queries through a cloud proxy to multiple third-party OTA platforms, which is network-capable behavior, yet no declared permission is present. This creates a transparency and governance gap: users and the platform may not have clear permission signaling for external data transmission, increasing privacy and policy risk even though the behavior appears aligned with the skill's stated purpose.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The sample trigger phrases are broad everyday travel requests such as asking flight prices between cities on a date, which can overlap with normal chat and cause accidental invocation. This is not a classic exploit, but it can lead to unintended external requests and user data being sent to the proxy/network flow without sufficiently explicit intent to use the skill.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The script contains a hard-coded proxy token used to authenticate outbound requests to a third-party proxy service. Embedding credentials directly in code risks accidental disclosure through source sharing, logs, package distribution, or repository leaks, allowing unauthorized use of the proxy and potentially exposing associated usage or billing.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
User-supplied flight search data is sent to an external proxy endpoint, but the code provides no visible disclosure, consent flow, or trust boundary indication to the user. While the data is not highly sensitive in all cases, travel intent and itinerary queries can still reveal personal preferences or plans, and routing through a proxy expands the exposure surface.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.