ClawHub
Back to skill

Security audit

极鲸云 Shein 品类搜索&分析

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed GeekBI SHEIN category-search integration with credential and install cautions, but no evidence of hidden, destructive, or unrelated behavior.

Install this only if you are comfortable with the skill contacting GeekBI's API, reusing/storing your GeekBI login state, and installing its Python dependency if missing. Use an isolated Python environment when possible, and only follow login links that are returned as part of the GeekBI authentication flow.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to read local files, invoke shell commands, run Python scripts, and access a remote service, yet it does not declare any permissions or constraints for those capabilities. This creates a trust and governance gap: reviewers and runtime policy may underestimate what the skill can do, increasing the chance of unintended command execution, filesystem access, or network exposure.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The auth state is persisted under a hard-coded different namespace (`temu-research-skill`) than the declared SHEIN skill. This can cause credential/state confusion across skills, leading to unintended token reuse, cross-skill access to another skill's login state, or accidental overwriting/clearing of auth material if multiple skills run in the same user environment.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description is broad enough to match many ordinary ecommerce or market-analysis conversations, so the skill may activate when the user did not intend to invoke it. Because activation leads to file reads, shell execution, and network-backed queries, accidental triggering increases the risk of unnecessary external calls and execution of local tooling in unrelated contexts.

Missing User Warnings

Low
Confidence
96% confidence
Finding
The skill tells the agent to run `python3 -m pip install -r requirements.txt` if dependencies are missing, which modifies the local environment and may introduce arbitrary package-install side effects. Without an explicit warning, isolation requirement, or package trust controls, this can lead to supply-chain risk, environment drift, and unexpected code execution during installation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.