huawei-cloud-cce-alarm-correlation-engine

• Outcome: Pass
• Latest audit: Aug 3, 2026 · 10:25 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed Huawei Cloud alarm-management tool with powerful but purpose-aligned cloud monitoring actions that require preview and confirmation.

Install this only for users authorized to inspect or manage Huawei Cloud AOM/CCE alarms. Prefer a least-privilege hcloud profile, avoid AK/SK environment fallback when possible, and review every preview carefully before confirming destructive cleanup or delete operations.

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
• 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 (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill clearly instructs use of shell execution (`python3 scripts/huawei-cloud.py` / local `hcloud`), environment-variable credentials, and generation of JSON input files, but the metadata shown does not declare corresponding permissions. That mismatch is a real security issue because an agent or platform may grant broader operational capability than reviewers or policy engines can see, undermining informed consent and permission-based isolation for cloud mutations.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The manifest exposes write and destructive capabilities such as create, update, delete, enable, disable, and bulk configuration of alarm and action rules without any embedded user-warning or approval semantics in the profile. In an observability/operations context, misuse could silence alerts, remove protections, or alter monitoring behavior, reducing visibility into outages or attacks and potentially causing prolonged undetected incidents.

Env Variable Harvesting

High

• Category: Data Exfiltration

Content

command.extend([f"--cli-access-key={access_key}", f"--cli-secret-key={secret_key}"])
    token = None
    if access_key and secret_key:
        token = os.environ.get("HUAWEI_SECURITY_TOKEN") or os.environ.get("HUAWEICLOUD_SDK_SECURITY_TOKEN")
    if token:
        command.append(f"--cli-security-token={token}")
    if proj_id:

• Confidence: 74% confidence
• Finding: This alternate environment variable source feeds the same security token into a CLI argument, creating the same local secret-exposure risk through argv inspection and endpoint telemetry. In an operations skill managing alarm rules and cloud state, leaked tokens could enable unauthorized API actions within the token's scope.

Env Variable Harvesting

High

• Category: Data Exfiltration

Content

command.extend([f"--cli-access-key={access_key}", f"--cli-secret-key={secret_key}"])
    token = None
    if access_key and secret_key:
        token = os.environ.get("HUAWEI_SECURITY_TOKEN") or os.environ.get("HUAWEICLOUD_SDK_SECURITY_TOKEN")
    if token:
        command.append(f"--cli-security-token={token}")
    if proj_id:

• Confidence: 74% confidence
• Finding: This alternate environment variable source feeds the same security token into a CLI argument, creating the same local secret-exposure risk through argv inspection and endpoint telemetry. In an operations skill managing alarm rules and cloud state, leaked tokens could enable unauthorized API actions within the token's scope.

VirusTotal

58/58 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.