ClawHub
Back to skill

Security audit

Discord

Security checks for vulnerabilities and agentic risk

Overview

The Discord connector is mostly coherent, but it needs Review because it combines account access with broad routing instructions and first-time setup commands that pipe remote install scripts into a shell.

Install only if you are comfortable connecting Discord through OOMOL and allowing the agent to read Discord account-related data. Manually review and install the oo CLI through a trusted, verifiable method instead of letting an agent run the remote installer commands, and require explicit approval before any write or destructive Discord action.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

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 recommends installing software via a remote script piped directly into a shell, which executes unverified code from the network without prior inspection. In an agent-assisted or automated context, this is especially dangerous because compromise of the hosting site, transport path, or installer content could lead to arbitrary code execution on the user's system.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill directs the agent to use this connector for ANY Discord-related request, creating an overly broad routing rule with little scope limitation. In an agent environment, this can cause unintended use of a powerful integration for requests that may require narrower authorization, additional validation, or user confirmation, especially if future actions are added beyond the currently listed read operations.

Static analysis

No suspicious patterns detected.