ClawHub
Back to skill

Security audit

极鲸云 Temu 图搜同款/商品图片搜索

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it sends user-provided product images to GeekBI to search Temu visually similar products, with expected network use and auth storage, but users should avoid sensitive images or private URLs.

Install only if you are comfortable sending the selected product images and related query parameters to GeekBI for processing. Do not use confidential, personal, customer, or private-network images or URLs unless you have authorization, and be aware that GeekBI login state may be stored locally for reuse by related skills.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to read local files or attachments, invoke shell commands, and make network requests, but no explicit permission declaration is present. That mismatch weakens policy enforcement and user visibility, increasing the chance that the skill accesses local data or external services without appropriate sandboxing or informed consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README encourages users to upload local images, attachments, URLs, Base64, and stdin content to perform image search, but it does not clearly disclose that those images are transmitted to an external third-party service (极鲸云). This creates a real privacy and data-handling risk because users may provide proprietary product images, supplier materials, customer content, or other sensitive media without informed consent about where the data goes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill accepts arbitrary http/https image URLs, fetches the remote content, and then uploads the bytes to a third-party API, but the code provides no explicit warning, consent gate, or provenance check before transmitting data off-host. This can cause unintended disclosure of sensitive images or internal-only resources if a user supplies a private URL or mistakenly assumes the image is processed locally.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.