Back to skill

Security audit

Linear

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Linear integration with sensitive account access and automation features, but the artifacts scope them to user-approved connections, writes, functions, and triggers.

Before installing, expect this skill to connect through Maton and Linear OAuth and to access business issue data. Approve only the account and scopes needed, confirm every mutation or automation before it runs, avoid unscoped triggers or third-party destinations unless you explicitly want ongoing forwarding, and prefer OAuth over long-lived API keys.

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
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 (1)

Vague Triggers

Low
Confidence
83% confidence
Finding
The instruction says to use this file when the user has connected the source and asks, by name, to act on its events, but it does not define specific trigger phrases or exclusion examples. For a markdown trigger-reference file, this leaves activation scope somewhat ambiguous and could lead to unintended use for broad requests involving Linear events.

Static analysis

No suspicious patterns detected.