discord-automation

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly uses Discord toolkit calls such as DISCORDBOT_LIST_MESSAGES and DISCORDBOT_LIST_MESSAGE_REACTIONS_BY_EMOJI (see "Core Workflows" and Quick Reference) which fetch user-generated Discord content (public/private messages, reactions) that the agent is expected to read and could materially influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The Rube MCP endpoint https://rube.app/mcp is required at runtime (RUBE_SEARCH_TOOLS) to fetch tool schemas that directly determine the agent's available tools/prompts and thus can dynamically control agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:18 AM