ClawHub
Back to skill

Security audit

极鲸云 Temu 类目搜索/品类搜索

Security checks across malware telemetry and agentic risk

Overview

This skill coherently searches Temu category data through GeekBI, with disclosed network calls and login-state reuse that fit its stated purpose.

Before installing, understand that this skill will run local Python scripts, contact GeekBI's API, and reuse/store GeekBI login state for authenticated queries. Install it only if you trust GeekBI with your Temu category research requests and are comfortable with shared GeekBI skill login 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
  • 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
93% confidence
Finding
The skill directs the agent to read local files, execute shell commands, install dependencies, and perform network-backed queries, yet it declares no corresponding permissions. This creates a capability/permission mismatch that can bypass least-privilege controls and increases the risk of unintended file access, command execution, or external data exfiltration if the skill is invoked in a broader agent environment.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The default prompt is broadly phrased to 'search and analyze Temu category opportunities' without clear user-trigger constraints or narrower activation conditions. In an agent environment, overly broad activation text can cause the skill to be invoked in loosely related commerce queries, increasing the chance of unintended tool use, irrelevant data access, or over-collection of external marketplace information.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.