ClawHub
Back to skill

Security audit

Tencent COS Uploader

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: uploads a user-chosen file to Tencent COS and returns temporary signed links, with the main risk being ordinary cloud-sharing exposure.

Before installing or running it, confirm the exact file, bucket, object key, and expiration time. Use least-privilege or temporary Tencent Cloud credentials, keep signed links short-lived, prefer HTTPS, and remember the uploaded object remains in your COS bucket until you delete it.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill performs sensitive operations that access environment variables for cloud credentials and initiates outbound network transfers to Tencent COS, yet it declares no permissions. This creates a transparency and consent gap: users or host systems may execute a file-uploading skill without an explicit indication that secrets and local data will be used for remote transmission.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill description explains functionality but does not prominently warn that running it will transmit a local file to a remote Tencent COS bucket and produce shareable presigned URLs. That omission increases the risk of accidental exfiltration of sensitive local data or unintended sharing, especially when invoked by users who only recognize terms like upload or temporary link without appreciating the security consequences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.