ClawHub

Trip Coupon 出行优惠券隐藏券-支持滴滴出行、携程礼包（机票、酒店、门票）

Security checks across malware telemetry and agentic risk

Overview

This mostly works like a travel coupon helper, but its bundled reference files also document unrelated food-delivery coupon flows and external redemption links, so users should review it before installing.

Install only if you are comfortable with a third-party coupon skill calling an external API and showing redemption links or QR codes. Check link destinations before opening them in WeChat or scanning QR codes. Prefer a corrected release that removes or fixes the unrelated takeout-coupon reference files so the package consistently matches its travel-coupon purpose.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Confidence
96% confidence
Finding
The documented API serves takeout coupons, while the skill is declared as a trip-coupon skill for ride and travel offers. This mismatch is security-relevant because it indicates the skill may invoke an endpoint outside its stated scope, misleading users and reviewers and creating a channel for undisclosed content delivery or bait-and-switch behavior. The explicit emphasis on preserving opaque coupon codes and external redemption flows further increases risk because users are encouraged to trust and act on unverified third-party content.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger phrases are broad enough to match generic travel or savings queries, which can cause the skill to activate when the user did not explicitly ask to retrieve third-party coupon links. That increases the chance of unsolicited network calls and exposing users to affiliate, tracking, or low-trust external redemption flows.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The documentation repeatedly steers users toward opening links or redeeming via QR code in WeChat without clear opt-in, necessity, or trust justification. In this skill context, that is risky because the API returns opaque third-party links, and pushing users into a specific external app can reduce scrutiny and increase phishing, tracking, or redirection risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal