ClawHub
Back to skill

Security audit

An interactive workflow structuring assistant that progressively clarifies and decomposes a vague process into a structured, executable workflow document.

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill helps users structure workflows through guided questions and does not request tools, credentials, persistence, or background execution.

Installers should expect this skill to ask for operational process details and organize them into structured documentation. Avoid sharing sensitive business or personal details unless they are needed for the workflow being documented, and be aware that broad process-related prompts may activate it.

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
93% confidence
Finding

The skill advertises broad trigger phrases like 'organize the process' and 'help me structure this process' without clear scope limits or exclusion conditions, so it may activate for many generic planning or operational requests. This can cause incorrect routing, unexpected invocation, and accidental collection or restructuring of sensitive operational details in contexts where a workflow-structuring skill was not intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.