Nozbe

• Outcome: Review
• Latest audit: Nov 3, 2026 · 10:51 AM UTC
• Version: 1.0.5

Overview

The Nozbe workflow requires approval for changes, but its automatic setup executes unverified remote code and under-discloses broader installation effects.

Review and install a version-pinned CLI separately, and instruct the agent to stop if it is missing. Check the CLI's bundled-skill installation and synchronization settings before use. Connect only the intended Nozbe account and retain approval for changes and deletions. The remote installers and hosted connector implementation remain unverified.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The only supplied command runs an Oomol-hosted installer, rather than accessing or managing Nozbe data. Although dependency installation can be a supporting implementation detail, this chunk provides no evidence connecting the installer to Nozbe. The remote script's contents and further effects cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High

• Category: Supply Chain
• Confidence: 99% confidence

Finding

The setup instructions pipe a mutable remote script directly into Bash without version pinning, integrity verification, or review; the PowerShell alternative has the same problem. If the distribution endpoint or delivery chain is compromised, this executes attacker-controlled code with the agent process's local permissions, potentially exposing files and credentials. The legitimate dependency and missing-CLI prerequisite limit when this occurs but do not make the execution safe.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

• oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

  bash

  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  

  powershell

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 91)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