Linearis

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward Linear CLI helper, but users should treat its token and write/delete commands carefully.

Before installing, make sure you trust the npm package and use a Linear API token with the narrowest practical scope. Do not let an agent run create, update, delete, upload, or download commands unless you explicitly asked for that action and understand which Linear workspace data or local files will be affected.

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: 90% confidence
Finding: The skill documents multiple state-changing and destructive commands, including create, update, delete, upload, and download operations, but provides no caution that these actions modify live Linear data or may have irreversible effects. In an LLM-agent context, this increases the chance of unintended writes or deletions because an agent may treat the examples as routine safe actions and execute them without confirmation.

Missing User Warnings

Medium

Confidence: 85% confidence
Finding: The authentication section instructs users to store or pass a personal API token but does not warn about credential sensitivity, shell history exposure, file permission risks, or avoiding token leakage in logs and agent output. In an agent-oriented skill, this is more dangerous because LLM systems may echo commands, capture environment variables, or mishandle secrets unless explicitly told not to.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal