ClawHub
Back to skill

Security audit

Automation Consultant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple automation-consulting skill description with broad marketing language but no code, hidden behavior, persistence, or credential handling.

Before installing, understand that this skill is more of a broad automation consulting description than a tightly scoped operational tool. Use it for business automation planning, and require explicit approval before it creates scripts, connects to APIs, posts content, sends email, or handles business/customer data.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file describes the skill with broad natural-language capability wording ('I help businesses automate workflows and save time') but does not specify when the skill should be invoked, what phrases should trigger it, or what requests are out of scope. In a skill-dispatch context, such generic wording can overlap with many ordinary business-assistance requests and increase the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The phrase 'And more!' expands the listed automation areas without defining limits, which weakens the specificity of the skill's scope. For markdown skill descriptions, this kind of open-ended wording can make it unclear what is or is not appropriate for the skill to handle.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.