Alicloud Security Cloudfw

• Outcome: Pass
• Latest audit: May 28, 2026, 9:39 AM
• Version:
  1.0.3

Overview

This skill is a coherent Alibaba Cloud Firewall management helper, but it can use cloud credentials for high-impact firewall changes.

Install only if you intend to let an agent help manage Alibaba Cloud Cloud Firewall. Use a dedicated least-privilege AccessKey, confirm the account, region, resource IDs, and intended changes before any mutation, and review any saved outputs for accidental sensitive data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill declares capabilities that include environment access, filesystem writes, and network use, but does not expose an explicit permissions model or user-facing disclosure for those actions. In a credentialed cloud-administration context, that creates real risk because the skill may read secrets from environment variables, contact external endpoints, and persist data locally without clear consent boundaries.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The skill claims to manage Cloud Firewall resources, but the documented executable path focuses on metadata discovery, downloading API information, and writing inventories to disk. That mismatch is security-relevant because users may authorize a firewall-management skill expecting direct operational behavior, while the skill instead performs broader documentation/network/file activities that expand attack surface and can mask unexpected behavior.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The workflow encourages create, update, modify, and set operations for firewall resources without an explicit warning that such changes can affect production traffic, security posture, and availability. In a firewall-management context, silent or insufficiently gated mutation guidance increases the chance of accidental disruptive changes or unauthorized policy modifications.

Missing User Warnings

Low

• Confidence: 80% confidence
• Finding: The skill instructs the use of AccessKey credentials from environment variables and shared config files but does not include a clear warning about sensitive secret handling, accidental logging, or persistence risks. In cloud-administration workflows, omission of those safeguards can lead to credential exposure through output artifacts, debug logs, or improper storage practices.

VirusTotal

50/50 vendors flagged this skill as clean.