discord-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires passing webhook_token (a secret) as a parameter to tool calls (e.g., DISCORDBOT_EXECUTE_WEBHOOK) which forces the LLM to handle and potentially output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow (e.g., “Send Messages” via DISCORDBOT_CREATE_MESSAGE with user-provided content) directly ingests outsider-authored free text supplied by the skill user into the Discord message payload without selecting a specific trusted item first.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the external MCP endpoint https://rube.app/mcp and explicitly instructs calling RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas, meaning remote content from that URL can directly control the agent's available tools and behavior.