ClawHub
Back to skill

Security audit

拼多多精选

Security checks across malware telemetry and agentic risk

Overview

This shopping skill is coherent: it sends user-requested Pinduoduo searches and product lookups to a disclosed cloud proxy and returns product information, without local data access, persistence, purchasing, or destructive behavior.

Install only if you are comfortable with your shopping searches and product identifiers being sent through the skill's cloud proxy. Avoid entering personal, account, payment, or order information; the artifact does not need those and says it cannot place orders or check logistics.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill declares environment-backed proxy configuration and clearly depends on network access, but no explicit permissions are documented. This creates a transparency and governance gap: reviewers and users cannot easily assess what outbound access the skill requires, and hidden network/env capabilities can enable unintended data flow through the proxy path. In this shopping context the data handled appears low sensitivity, which reduces severity, but the undeclared capability is still a real security issue because it obscures trust boundaries.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
User-supplied search terms and product identifiers are transmitted to an external proxy service, but the tool provides no user-facing disclosure that queries leave the local skill boundary. In a shopping context this can expose user interests, browsing intent, and identifiers to a third party, creating a privacy and data-governance risk even if the transfer is functionally necessary.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.