ClawHub
Back to skill

Security audit

huawei-cloud-cce-alarm-correlation-engine

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Huawei Cloud alarm-management skill that can change monitoring rules only through a preview-and-confirm workflow.

Use a least-privilege Huawei Cloud profile for the task, preferably read-only for inspection. Review mutation previews carefully before allowing confirm=true, especially for disabling or deleting alarm and notification rules, and avoid broad administrator credentials or sharing AK/SK values in chat or logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly instructs use of shell execution (`python3 scripts/huawei-cloud.py`), environment-based credentials, and generated JSON input files, which means it has operational capabilities to access secrets and perform cloud mutations. Because these capabilities are present but no declared permissions are provided, the host system cannot enforce least-privilege or clearly signal the risk boundary, increasing the chance of unintended command execution, credential exposure, or unauthorized alarm-rule changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.