ClawHub
Back to skill

Security audit

Task Queue Manager Free

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local task-queue helper whose file persistence and command use fit its stated purpose, though users should be mindful that queued payloads and results are stored on disk.

Install only if you want an agent-managed local task queue. Avoid putting secrets, regulated personal data, or confidential business records into queued payloads unless you are comfortable with those values being written under workspace/tasks and possibly retained in done or failed logs. Review generated commands and any example code before running it, especially for database writes or external API calls.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger scope is overly broad and includes generic project-management and workflow terms, which can cause the skill to activate in contexts far beyond durable local task queues. In an agent environment with exec capability, over-triggering increases the chance of unintended file creation, task persistence, or command execution on user data without clear intent.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill persistently writes task payloads, results, failure data, and lock state to local files, but it does not clearly warn users that potentially sensitive data will be stored on disk. This can lead to inadvertent retention of personal data, secrets, or business information in workspace files that may later be exposed, backed up, or committed.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The examples include syncing user data and calling external APIs, but they omit warnings about transmitting personal or sensitive information to third parties and storing related payloads locally. In practice, users may copy these patterns directly and unintentionally expose regulated or confidential data through outbound requests and persistent logs.

Static analysis

No suspicious patterns detected.