ClawHub
Back to skill

Security audit

workspace-health-monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only workspace health checker that reports local file metrics and selected paths, with no evidence of hidden persistence, mutation, credential use, or network exfiltration.

Before installing, understand that this skill reads through the target workspace and may print file or directory names in its report. Avoid running it from a directory containing sensitive project names or secret-bearing filenames if that output may be shared.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill recursively enumerates the entire workspace and reports detailed file-path metadata, including large file paths and empty directory names, directly to stdout with only a generic health-check message. In shared, multi-tenant, or sensitive workspaces, this can disclose internal project structure, secret-bearing filenames, or other metadata beyond what a user may expect from a routine health check.

Content

No source excerpt is available for this finding.