ClawHub
Back to skill

Security audit

极鲸云 Shein 店铺搜索&分析

Security checks across malware telemetry and agentic risk

Overview

This skill appears to perform the advertised SHEIN shop research, but it reuses and stores GeekBI login state in a mismatched TEMU-named auth directory, which users should review before installing.

Install only if you are comfortable with the skill running local Python scripts, contacting GeekBI's API, and reusing/storing GeekBI login state on this machine. Pay particular attention to the TEMU-named auth directory because it may share or affect login state used by other GeekBI skills.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill invokes local files, shell commands, Python scripts, package installation, and network-backed queries, but the metadata does not declare corresponding permissions or capabilities. This creates a transparency and policy-enforcement gap: a host may allow the skill to run without clearly signaling that it can execute commands, read local resources, and access external services, increasing the chance of unintended code execution or data exposure.

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The auth state is stored under a product-specific directory named "temu-research-skill" even though this skill is for SHEIN shop search. This can cause credential/state confusion across unrelated skills, leading to unintended token reuse, accidental cross-skill access, or one skill clearing/overwriting another skill's authentication state on the same host.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.