Back to skill

Security audit

Linear MCP

Security checks for vulnerabilities and agentic risk

Overview

The Linear workflow is coherent, but its setup directs execution of unverified downloaded code without a separate installation approval step.

Review and approve CLI installation separately, including any changes to other agent skills. Prefer a reviewed, fixed release and grant only necessary Linear permissions. OOMOL mediates the connection and requests; the remote installer and server-side credential protections could not be verified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command installs software from an external Oomol endpoint; it does not show any Linear MCP operations or establish that this installation supports them. Remote installer execution is a material capability not represented by the declared description. The downloaded script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

The supplied chunk contains no Linear MCP interaction or Linear data operations. Authentication could be a supporting implementation detail, but nothing in this chunk establishes that oo auth login authenticates to Linear or supports the declared workflow.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote code without checking a pinned version, signature, or independently trusted digest; the PowerShell alternative has the same issue. A compromised installation endpoint or release pipeline could execute arbitrary commands with the user's privileges, although the supplied content does not establish that the endpoint is malicious.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning about system-level effects.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The missing-CLI fallback directs installation through remotely downloaded shell or PowerShell code without a separate approval requirement or explanation of host changes. Although conditional and relevant to setup, this expands a Linear data task into code execution with the invoking user's privileges; the Linear write-confirmation rules do not cover this installation.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources