ClawHub
Back to skill

Security audit

Linear CLI专家

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a Linear automation guide, but it gives agents broad issue-changing and credential-handling authority while under-scoping when and how that authority should be used.

Review before installing. Use this only when you explicitly want an agent to operate Linear through the local linear CLI, and expect it to use your existing Linear credentials to read or change issues, labels, comments, states, and related workspace data. Avoid running token-retrieval examples in logged shells, and require preview or dry-run confirmation before any write or bulk operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill declares itself as pure Markdown-driven at the end, while the rest of the document clearly instructs the agent to use exec, write files under /tmp, call external APIs, and handle authentication state. This misclassification can bypass user or platform expectations about side effects, causing an agent to execute commands or perform networked mutations when a reviewer believed the skill was documentation-only.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation language is overly broad, covering generic coding, debugging, testing, and deployment scenarios rather than narrowly scoping to explicit Linear CLI tasks. In agent environments, broad triggers increase the chance the skill is invoked in unrelated contexts, leading to unnecessary command execution, network access, or issue mutations with authenticated credentials.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents token retrieval and auth-recovery flows, including use of 'linear auth token' and relogin via environment variables, without a strong warning not to print, log, or persist secrets. In an agent context, such guidance can lead to accidental exposure of bearer tokens in terminal output, execution logs, or downstream tools.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.