discord-automation

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses a remote MCP endpoint at https://rube.app/mcp, which serves as the core infrastructure for the automation service described.
  • [PROMPT_INJECTION]: The skill provides an interface for processing untrusted Discord content, which is a surface for indirect prompt injection. 1. Ingestion points: Discord messages and reaction data are retrieved via listing tools (SKILL.md). 2. Boundary markers: No specific delimiters or instructions to ignore embedded content are provided. 3. Capability inventory: The tools allow for significant actions such as managing guild roles and executing webhooks. 4. Sanitization: There is no mention of input sanitization for data obtained from Discord.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:45 AM
Security Audit — agent-trust-hub — discord-automation