ClawHub
Back to skill

Security audit

1.2.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple incident-triage playbook with templates and harmless version/healthcheck scripts, not a hidden or privileged automation package.

Installers should understand this is guidance and templates rather than a working incident-management CLI. Verify that any referenced triage or workflow commands exist in your own environment before relying on them during an incident.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The declared description describes an incident triage workflow for outages and error alerts, but the supplied code does not implement any triage, alert handling, or runbook behavior. Its only function is to echo a version string. That is a materially different primary purpose from the declared description, so this is a mismatch.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The declared description says this skill performs incident triage for service outages and high-error alerts, implying operational logic, alert handling, and runbook-oriented workflow behavior. The supplied code does none of that: it only echoes a fixed string and does not inspect alerts, triage incidents, access service state, or execute any runbook steps. This is a clear material mismatch in primary purpose and implemented capability.

Static analysis

No suspicious patterns detected.