ClawHub
Back to skill

Security audit

Aliyun Platform Docs Review

Security checks across malware telemetry and agentic risk

Overview

This skill mainly performs a public documentation review, but it unnecessarily asks users to configure Alibaba Cloud access keys and mentions mutating operations that are not justified by the visible workflow.

Review before installing. Use it only if you are comfortable with a script fetching Alibaba Cloud public documentation pages and writing local report files. Do not provide Alibaba Cloud access keys for this skill unless the publisher documents exactly why they are needed, which read-only permissions are required, and what operations will use them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes a Python script that performs network access and writes artifacts to disk, but the skill metadata declares no permissions or equivalent capability constraints. This mismatch can cause operators or automated policy systems to treat the skill as less risky than it is, increasing the chance it runs with insufficient review and broader-than-expected access.

Intent-Code Divergence

Medium
Confidence
86% confidence
Finding
A documentation review skill should be read-only, yet the prerequisites mention cloud credentials and refer to asking before running mutating operations. That language suggests the underlying workflow may include account-authenticated or state-changing cloud actions beyond simple doc retrieval, creating ambiguity that could lead to unintended use of privileged credentials or accidental modification of cloud resources.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.