ClawHub
Back to skill

Security audit

WS QuickStatus

Security checks for vulnerabilities and agentic risk

Overview

This skill runs a small, disclosed workspace status check and does not install code, persist changes, or contact external services.

Before using it in a sensitive workspace, be aware that the status output can reveal filenames from recent memory notes and deliverable directories. It appears safe for normal workspace orientation, but avoid sharing its output externally if filenames may contain client, incident, or private task details.

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

Low
Confidence
88% confidence
Finding
The skill explicitly lists the last three files under `memory/*.md`, which can reveal the existence and names of recent memory notes. Even without printing file contents, filenames often contain task names, clients, incidents, or other sensitive context, so exposing them by default can disclose information to anyone invoking the skill.

Static analysis

No suspicious patterns detected.