Linear 1.0.0

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:20 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed Linear helper that reads and updates Linear work items using a user-provided API key, with one low-risk local cache hardening issue.

Install only if you are comfortable giving the agent the permissions attached to your Linear API key. Use the least-privileged key available, require explicit approval for create/comment/status/priority/assign commands, and set LINEAR_TEAMS_CACHE to a private path on shared systems.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

• Confidence: 93% confidence
• Finding: The script caches team metadata in /tmp using a predictable filename derived from the API key checksum and does so without setting restrictive permissions or validating the target path. On multi-user systems, this can expose organizational team information to other local users and creates symlink/race-file risks if an attacker can pre-create or replace the cache path.

VirusTotal

64/64 vendors flagged this skill as clean.