ClawHub

qshell-copilot

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Qiniu cloud-storage helper, but users should treat its storage commands and Qiniu keys carefully.

Install this only if you want an assistant to operate qshell against your Qiniu account. Use least-privilege Qiniu keys when possible, avoid pasting secrets into chat, verify qshell from an official source, and review bucket names, object keys, overwrite, move, delete, CDN refresh, and bucket-creation commands before approving them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger text is broad enough to capture generic cloud-file requests such as 'upload this to my bucket' or 'list my cloud files' when Qiniu is only inferred from context. That can cause the agent to invoke a powerful storage-management skill in ambiguous situations, increasing the chance of unintended remote operations, data disclosure, or destructive actions against the wrong provider/account.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs direct entry of AccessKey and SecretKey into a command without warning about credential sensitivity, storage risks, shell history exposure, or safer alternatives. In an agent setting, this can normalize collecting or echoing long-lived secrets into logs, transcripts, terminal history, or tool traces, leading to credential compromise and full access to the user's Qiniu resources.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal