ClawHub
Back to skill

Security audit

linear-native-node

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Linear helper that uses a user-provided Linear API key to read and, only with an explicit execute flag, modify Linear issues and projects.

Install only if you want an agent to access your Linear workspace through LINEAR_API_KEY. Use the least-privileged Linear key available, prefer passing --team or setting LINEAR_DEFAULT_TEAM to limit reads, and approve --execute commands only when the exact Linear change is intended.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Ae1

High
Category
analysis-evasion
Content
Use `scripts/linear.mjs` to talk directly to Linear's GraphQL API at `https://api.linear.app/graphql`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
Use `scripts/linear.mjs` to talk directly to Linear's GraphQL API at `https://api.linear.app/graphql`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
Use `scripts/linear.mjs` to talk directly to Linear's GraphQL API at `https://api.linear.app/graphql`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
Use `scripts/linear.mjs` to talk directly to Linear's GraphQL API at `https://api.linear.app/graphql`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
Use `scripts/linear.mjs` to talk directly to Linear's GraphQL API at `https://api.linear.app/graphql`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
Use `scripts/linear.mjs` to talk directly to Linear's GraphQL API at `https://api.linear.app/graphql`.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
`1.0.6`: Package-only cleanup: publish runtime files plus packaging metadata (`SKILL.md`, `.clawhubignore`, and `scripts/linear.mjs`) and keep the local test h
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly requires environment-variable access and outbound network access, but the manifest/frontmatter does not declare an explicit tool scope such as permissions or allowed-tools. That creates a policy gap where reviewers or execution frameworks may not understand or constrain the skill's real capabilities, increasing the chance of over-privileged or insufficiently reviewed execution.

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: linear-native-node
description: Linear workspace helper using Linear's GraphQL API from native Node.js. Use when creating, listing, updating, commenting on, summarizing, or looking up Linear issues, projects, teams, workflow states, priorities, standup notes, or branch names. Write actions are explicit and approval-gated via create/comment/status/priority/project-create commands. Reads LINEAR_API_KEY from the process environment only; no OAuth gateway, bash, Python, npm dependencies, or third-party intermediary/proxy service.
version: 1.0.22
risk_class: external-api-read-write-gated
---
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

External Transmission

Medium
Category
Data Exfiltration
Content
// Linear GraphQL helper - native Node.js, zero dependencies.
// Requires Node 18+ for global fetch. Reads LINEAR_API_KEY from the process environment only.

const ENDPOINT = "https://api.linear.app/graphql";
const PRIORITIES = new Map([
  ["none", 0],
  ["urgent", 1],
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
// Linear GraphQL helper - native Node.js, zero dependencies.
// Requires Node 18+ for global fetch. Reads LINEAR_API_KEY from the process environment only.

const ENDPOINT = "https://api.linear.app/graphql";
const PRIORITIES = new Map([
  ["none", 0],
  ["urgent", 1],
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
// Linear GraphQL helper - native Node.js, zero dependencies.
// Requires Node 18+ for global fetch. Reads LINEAR_API_KEY from the process environment only.

const ENDPOINT = "https://api.linear.app/graphql";
const PRIORITIES = new Map([
  ["none", 0],
  ["urgent", 1],
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/linear.mjs:35