huawei-cloud-maas-tokens-usage

• Outcome: Review
• Latest audit: Jun 10, 2026 at 9:44 AM UTC
• Version:
  0.0.1

Overview

This skill does the advertised Huawei Cloud MaaS usage lookup, but its script disables HTTPS certificate verification while using cloud credentials.

Install only if you are comfortable reviewing or patching the helper script first. Remove verify=False, do not print credential files, use least-privilege Huawei Cloud keys, and confirm the skill is invoked only for Huawei Cloud MaaS usage queries.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The trigger list includes broad terms like request count, error count, tokens usage, and statistics, which could activate the skill for unrelated monitoring or token/accounting requests. Over-broad invocation increases the chance the agent runs a credentialed cloud-query skill in the wrong context, exposing metadata or causing unintended external calls.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The example explicitly disables TLS certificate verification with `verify=False`, which allows man-in-the-middle interception or tampering of supposedly HTTPS-protected API traffic. In this skill’s context, the request is authenticated with AK/SK-style signed headers and may expose sensitive request metadata or enable response spoofing, so presenting this as a troubleshooting example without a strong warning is unsafe.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documentation includes credential-handling examples that encourage users to inspect or provide secrets without any warning about sensitive data exposure. In particular, showing a command like `cat /path/to/aksk.txt` normalizes printing secret material to the terminal, shell history, logs, or screenshots, which can lead to accidental credential disclosure.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The end-to-end verification script performs a real authenticated API call using a hardcoded local credential file path, but provides no warning about secret handling, file permissions, or the risks of embedding local paths in shared documentation. This can encourage unsafe practices such as storing long-lived credentials in predictable locations and running examples that expose secrets through process arguments, logs, or copied scripts.

Missing User Warnings

Medium

• Confidence: 99% confidence
• Finding: The code disables TLS certificate verification for all HTTPS requests to IAM and MaaS endpoints, which allows a man-in-the-middle attacker to intercept or alter supposedly secure traffic. In this skill, those requests include signed cloud API calls and usage data queries, making the context especially sensitive because credentials and returned statistics could be exposed or tampered with.

VirusTotal

65/65 vendors flagged this skill as clean.