ClawHub
Back to skill

Security audit

Cos_Uploader_Qcloud_lh

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it says, but it can upload a message-specified local file path to Tencent COS without tightly limiting it to received photo cache files.

Review before installing in production. Use a least-privilege Tencent COS sub-account limited to the intended bucket, keep the bucket private, protect and rotate local secrets, and add path validation so only canonical files under the OpenClaw inbound media cache and actual image content can be uploaded. Also document consent and retention expectations for people sending photos through WeChat.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README describes automatic receipt and cloud upload of WeChat photos but does not clearly warn operators that this processes potentially sensitive user images and stores them in a third-party cloud service. In this context, the omission can lead to deployment without informed consent, retention review, or privacy controls, increasing the risk of privacy violations and unintended exposure of personal data.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The README explains that COS credentials are encrypted and stored locally, but it does not prominently warn that long-lived cloud secrets and the encryption key reside on the same host. That can create a false sense of security for operators, who may overlook host compromise risk, backup leakage, or the need for stronger secret-management practices.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.