ClawHub
Back to skill

Security audit

Kubernetes Diagnostics

Security checks for vulnerabilities and agentic risk

Overview

This skill provides purpose-aligned Kubernetes diagnostics, with no evidence of hidden collection, destructive actions, or persistence.

Use a read-only Kubernetes identity limited to the intended clusters and namespaces. Apply the skill only within a Kubernetes request, select the target context explicitly, and review logs and configuration output before sharing them. The skill's diagnostic examples do not require mutation authority.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

python
get_nodes_summary()

kubeconfig_view()

list_contexts()

Activation keywords include everyday phrases without an explicit Kubernetes-context requirement.

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

The activation rules include generic phrases such as "how much" and "difference between" without requiring Kubernetes context, potentially causing unrelated requests to trigger cluster diagnostics. The Kubernetes-specific title and description reduce this risk, but keyword-only activation could still lead to unnecessary cluster access or disclosure of operational information in responses.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.