discord-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires passing secret tokens (e.g., webhook_token and toolkit/bot tokens via the Discord toolkits) as parameters for tool calls like DISCORDBOT_EXECUTE_WEBHOOK, which forces the agent to include secret values verbatim in outputs/tool calls and creates an exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting the Rube MCP endpoint (https://rube.app/mcp) at runtime—via RUBE_SEARCH_TOOLS—to fetch tool schemas that directly determine available tools/instructions, so the external content controls agent prompts and is a required dependency.