ClawHub
Back to skill

Security audit

K8s集群管理专业版

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Kubernetes operations skill, but it asks for broad execution/write authority and uses overly broad activation wording for high-impact cluster changes.

Install only if you intend to let the agent help manage Kubernetes environments. Before use, restrict kubeconfig contexts and API tokens to the minimum clusters and namespaces needed, require confirmation before enforce, deploy, CRD install, prune, self-heal, or backup changes, and verify any referenced scripts or requirements because they are not included in this artifact.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation guidance repeatedly uses broad 'Use when' phrasing for common activities like monitoring, logging, alerting, and deployment, with little narrowing or exclusion logic. In an agent ecosystem, this can cause the skill to be invoked in many ordinary contexts and expose powerful exec/write capabilities more often than intended, increasing the chance of unsafe or unnecessary command execution.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill declares coverage for a very long list of generic scenario keywords without meaningful exclusion criteria or disambiguation. That ambiguous scope can over-trigger the skill for unrelated enterprise, automation, monitoring, or development requests, which is risky because the skill advertises command execution and external integrations.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.