Back to skill

Security audit

Livespace

Security checks for vulnerabilities and agentic risk

Overview

The Livespace workflow includes useful safeguards, but its setup fallback runs unverified internet scripts without requiring your approval.

Review the setup fallback before installing. Install an independently reviewed, version-pinned CLI yourself and require approval for installer execution. OOMOL mediates the Livespace account connection; retain the skill's write and deletion confirmations. The downloaded installer contents and effects were not 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied command installs software from an Oomol-hosted endpoint rather than performing Livespace operations. Nothing in the provided code establishes this installer as a supporting dependency for Livespace. The downloaded script's contents and subsequent effects are not supplied, so those effects cannot be assessed.

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 content without integrity verification or review; the PowerShell alternative has the same weakness. Compromise of the installer distribution infrastructure could yield arbitrary execution with the agent's local privileges, exposing accessible files and credentials; HTTPS alone does not protect against a compromised origin.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning the user about running remote code or modifying their system.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The missing-CLI recovery workflow directs the agent to execute remote installation scripts without requiring approval for code execution or system changes. Its conditional nature limits exposure, but routine setup can still become unauthorized local code execution; the Livespace write confirmations do not cover 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 101)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