ClawHub
Back to skill

Security audit

极鲸云 Shein 商品搜索&分析

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a legitimate SHEIN product-search integration, but it reuses and persists login state in a Temu-named namespace, so users should review that credential behavior before installing.

Install only if you are comfortable with this skill reusing existing GeekBI login state and making authenticated requests to GeekBI's API. The main review item is the credential store: it may read or write auth state shared with another GeekBI/Temu-named skill path, so use an isolated profile or clear the .geekbi auth state if you do not want cross-skill session reuse.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill explicitly instructs the agent to read local reference files, invoke Python scripts, and rely on networked backend services, yet no declared permissions are present. This creates a governance gap: the platform and reviewer cannot accurately constrain or audit what the skill is allowed to access, increasing the risk of unintended file access, command execution, or outbound requests if the skill is misrouted or modified.

Intent-Code Divergence

Medium
Confidence
90% confidence
Finding
The auth state is stored under a different namespace ('temu-research-skill') than the current SHEIN-related skill. This can cause credential/state collision across unrelated skills, leading to accidental token reuse, cross-skill authentication confusion, or unintended access to another skill's persisted login state on the same machine.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The description contains broad trigger phrases covering many common product-research intents such as search, selection, hot products, new products, competition, and comparisons. Overbroad activation boundaries can cause the skill to run in contexts the user did not clearly intend, which is more dangerous here because the skill can read files, execute scripts, and make network-backed queries.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.