ClawHub
Back to skill

Security audit

Setup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward workflow setup helper that creates a project workflow document and lightly updates project guidance, with no evidence of hidden or malicious behavior.

Before installing, expect it to read project planning/config files and to create docs/workflow.md. It may also edit CLAUDE.md to reference that workflow, so review that diff if CLAUDE.md controls agent behavior in your project.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises 'zero interactive questions' and performs file writes/edits (`docs/workflow.md`, `CLAUDE.md`) but does not give an upfront warning in its user-facing description that it will automatically modify project files. This can lead users to invoke it without informed consent, increasing the risk of unintended overwrites or repository changes, especially because the skill is positioned as an automatic setup step after scaffolding.

Static analysis

No suspicious patterns detected.