ClawHub
Back to skill

Security audit

Convex

Security checks for vulnerabilities and agentic risk

Overview

This Convex skill is mostly transparent, but it needs review because it can run powerful Convex operations and its safety labels understate some mutation or execution actions.

Review before installing. Use it only if you trust OOMOL with Convex access, avoid automatic pipe-to-shell CLI installation, and require explicit approval before any deploy key, project/deployment deletion, function, action, or mutation execution.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

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
97% confidence
Finding
The skill instructs fetching and executing a remote install script via `curl ... | bash`, which is a classic supply-chain and arbitrary code execution risk. If the remote server, network path, or script content is compromised, the agent could run attacker-controlled code on the host with the current user's privileges.

Static analysis

No suspicious patterns detected.