ClawHub
Back to skill

Security audit

Simple Analytics

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its Simple Analytics purpose, but its fallback setup can run an unverified remote installer automatically.

Review this skill before installing if you are not comfortable with an agent being told to install the oo CLI through remote shell commands. Prefer manually installing the CLI from trusted OOMOL instructions, verify the installer where possible, and require confirmation before any setup, login, connection, or write action such as sending events.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Content
- **`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
Confidence
98% confidence
Finding
The skill instructs the agent to execute a remote installation script via `curl ... | bash`, which is a classic supply-chain risk because downloaded code is executed immediately without verification. This is especially dangerous in an agent skill because the setup guidance may be followed automatically after an error path, turning a documentation snippet into command execution from a network source.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The manifest description instructs the agent to use this skill for ANY Simple Analytics request, including reads, creates, and updates, which is overly broad and can cause the skill to be invoked in situations where a narrower or safer flow should be chosen. In context, this is more dangerous because the skill includes write-capable actions, so over-triggering increases the chance of unintended state-changing operations or unnecessary exposure to setup/install guidance.

Intent-Code Divergence

Low
Confidence
92% confidence
Finding
Line L40 describes `export_data_points` as exporting raw datapoints from the Simple Analytics Export API, which semantically indicates data retrieval rather than a state-changing operation. Tagging it as `[write]` contradicts the stated action behavior and could cause unnecessary or misleading user confirmation flows.

Static analysis

No suspicious patterns detected.