Security audit

Kyaukyuai Linear Cli

Security checks across malware telemetry and agentic risk

Overview

This skill is a documented Linear CLI helper that can read and change Linear data, with no bundled executable code or hidden install behavior.

Install this only if you want an agent to operate your Linear workspace through the local linear CLI. Use dry-run or explicit confirmation for issue, project, comment, webhook, label, and raw API changes, and avoid broad invocations unless you specifically intend Linear operations.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger keywords are very broad and generic (`read`, `runtime`, `agent`, `cli`), which can cause this skill to activate in unrelated contexts. Because the skill exposes `exec` and supports mutating remote Linear data, overbroad activation increases the chance an agent invokes powerful functionality when the user did not specifically intend to use this integration.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The description emphasizes productivity and safety claims but does not clearly warn that the skill can create, update, and otherwise mutate remote Linear data. In an agent setting, this omission can mislead users or orchestrators into treating the skill as read-oriented, increasing the risk of unintended writes to production project-management data.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.