ClawHub

Qclaw Cloud Backup

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed QClaw/Tencent SMH cloud-upload helper for user-selected files, with no evidence of hidden exfiltration or destructive behavior.

Install only if you intend to use QClaw/Tencent SMH cloud storage for selected files. Confirm the exact local path before uploading, avoid sensitive files unless off-device storage is acceptable, and review generated links before sharing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares no permissions while clearly directing the agent to execute shell commands (`bash`/`cmd`, `curl`, and implicitly `node`/`jq`). This creates a capability/permission mismatch that can bypass user or platform expectations about what the skill is allowed to do, especially because it can access local file paths and transmit their contents to cloud storage.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad everyday expressions such as '发到手机' or '做完了发我一份', which can match normal conversation rather than an explicit request to upload local files to cloud storage. In this skill's context, accidental invocation is more dangerous because the action can cause real data exfiltration from the local system to a remote cloud service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill does not prominently warn users that selected local files are transmitted to Tencent SMH and become viewable in QClaw. This disclosure gap undermines informed consent and increases the risk of users unintentionally uploading sensitive personal or enterprise data under the mistaken belief that the operation is local or temporary.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal