ClawHub
Back to skill

Security audit

Write A Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple instructional skill for helping users draft agent skill packages, with no executable code, hidden behavior, or privileged access.

Before installing, note that this skill may guide your agent to create new skill files and optional helper scripts as part of normal skill development. Review generated skills before using or publishing them, especially if they include executable scripts.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says, "Use when user wants to create, write, or build a new skill," which is a broad natural-language trigger without clear boundaries or exclusions. While domain-related, it does not specify what counts as a "skill" or provide negative examples, increasing the chance of unintended invocation for generic writing or building requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.