ClawHub

Linear Agent

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it lets an agent read and change Linear workspace items using your Linear API key.

Install only if you want your agent to act in Linear with the permissions of your API key. Use the least-privileged key available, review requests before running write commands such as update-issue, move-issue, post-comment, create-project, and sync-commit, and revoke the key if you stop using the skill.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The manifest advertises capabilities to create, update, move, and comment on Linear issues and projects using a personal API key, but it does not clearly warn users that the skill can modify live workspace data. This creates a real risk of users authorizing destructive or unintended changes without informed consent, especially because the scope includes broad project-management mutations across teams, cycles, and projects.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill requires a secret LINEAR_API_KEY but provides no privacy or data-transmission notice explaining that workspace data and user-supplied content will be sent to Linear's remote API. Users may supply a personal key without understanding what data is accessed or modified, increasing the risk of unauthorized disclosure or misuse of workspace information under their account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal