Aliyun Green Moderation

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed Alibaba Cloud Content Moderation helper that uses expected cloud credentials and writes local API metadata artifacts.

Install only if you intend to manage Alibaba Cloud Green moderation resources. Use a least-privilege Alibaba Cloud key or role, confirm the target region and resource IDs before create/update actions, and review any files saved under output/aliyun-green-moderation/.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill instructs use of environment credentials, local file output, and network-based OpenAPI access, but does not declare corresponding permissions. This creates hidden capability risk: an agent or reviewer may approve the skill without realizing it can access secrets, write artifacts, and contact external services, which weakens least-privilege controls and auditability.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The skill advertises management of Alibaba Cloud Green resources and troubleshooting workflows, but the described executable path centers on metadata discovery and local documentation generation instead of the claimed operational tasks. This mismatch is dangerous because users and orchestrators may invoke the skill for privileged cloud-management actions while it performs different network activity, undermining informed consent, policy review, and reliable security scoping.

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: The invocation description is broad enough to capture many generic moderation-management requests, increasing the chance the skill is selected outside a narrowly intended context. In combination with credential use, file writing, and network access, over-broad routing can cause unnecessary exposure of cloud credentials or unintended external calls for tasks that do not require this specific skill.

VirusTotal

66/66 vendors flagged this skill as clean.