ClawHub
Back to skill

Security audit

Linear同步(免费版)

Security checks across malware telemetry and agentic risk

Overview

This Linear CLI skill mostly matches its stated purpose, but its permissions and activation scope are broader than a user would reasonably expect.

Review this skill before installing if your Linear workspace contains sensitive team or project data. Use it only when you explicitly want Linear CLI actions, confirm any issue creation before execution, and prefer a version whose manifest permissions and trigger language are narrowed to Linear-specific tasks.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Scope Creep

Low
Confidence
93% confidence
Finding
The manifest declares `allowed-tools: read exec` but later also lists `write`, creating a permission mismatch that can cause reviewers or policy engines to underestimate the skill's actual capabilities. In an exec-enabled skill, undocumented write access materially increases risk because the agent could modify local files, configs, or prompts while users expect a read/exec-only tool.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The top-level description uses broad activation language such as project management, planning, progress tracking, and collaboration, which can cause the skill to trigger in many ordinary contexts beyond Linear-specific requests. Over-broad routing is dangerous because it may invoke an exec-capable external CLI with authenticated access when the user did not intend to use Linear or authorize live system actions.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The capability coverage section enumerates a long keyword list and vague trigger phrases without constraints, making the skill appear applicable to many unrelated user prompts. This increases the chance of accidental invocation of a tool that can execute commands and act against a real Linear workspace, potentially causing unintended data access or issue creation.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.