ClawHub
Back to skill

Security audit

Alibaba Cloud Media VOD

Security checks across malware telemetry and agentic risk

Overview

This Alibaba Cloud media-management skill appears purpose-aligned, but it gives agents deletion and production-configuration authority without enough explicit safeguards.

Install only if you intend to let the agent administer Alibaba Cloud VOD resources. Use read-only or tightly scoped credentials by default, prefer short-lived STS credentials, and require explicit confirmation of exact VideoIds and account/environment before any delete, update, callback, template, or billable processing action.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill uses environment credentials, writes local evidence files, and accesses external network resources, but it does not declare these capabilities or permissions. This creates a transparency and governance problem: operators may invoke it without understanding that it can read cloud credentials, contact external Alibaba endpoints, and persist potentially sensitive operational data.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The skill instructs use of AccessKey/STS credentials from environment variables and shared credential files without an explicit warning not to log, persist, or expose those secrets. In a skill that also writes evidence files, this increases the risk that credentials or derived sensitive configuration details could be accidentally captured or disclosed.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The workflow includes mutation-capable and potentially destructive operations such as update, delete, template changes, callback changes, and media processing, but it lacks a clear warning about impact to user media assets and production configurations. In a cloud media management context, an incorrect or automated invocation could delete assets, alter playback authorization, or trigger costly jobs.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The template includes a `DeleteVideo` operation with no warning, confirmation guidance, or scope-limiting safeguards despite being an irreversible destructive action. In an agent skill context, templated deletion steps can be copied directly into workflows, increasing the chance of accidental or overly broad media deletion, especially when multiple IDs are accepted in one request.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.