ClawHub
Back to skill

Security audit

discord-bot

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a Discord message-posting skill, but its trigger guidance is too broad and its referenced bot script is not included in the package.

Review before installing. Use this only for explicit Discord posting tasks, verify the missing bot script before running it, use a least-privileged Discord bot token, and avoid sending sensitive or private content through the skill.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: jpeng-discord-bot
description: "Send messages to Discord"
version: "1.0.0"
author: "jpeng"
tags: ["chat", "discord", "communication"]

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
---
name: jpeng-discord-bot
description: "Send messages to Discord"
version: "1.0.0"
author: "jpeng"
tags: ["chat", "discord", "communication"]

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation describes sending messages to Discord and requiring an API key but does not warn users that content will leave the local environment and be transmitted to an external service. Without a clear notice, users or calling agents may send sensitive information through the skill without informed consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's invocation guidance is broad enough that it could be selected for generic 'chat' or 'communication' tasks without the user clearly intending to send data to an external Discord service. That increases the chance of unintended disclosure of prompts, outputs, or sensitive workflow data to a third-party platform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.