discord-automation

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Discord, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The agent is instructed to read Discord messages, DMs, and reactions using tools like DISCORDBOT_LIST_MESSAGES and DISCORDBOT_LIST_MESSAGE_REACTIONS_BY_EMOJI (referenced in SKILL.md).
  • Boundary markers: The skill lacks instructions for implementing delimiters or "ignore embedded instructions" warnings when processing message content.
  • Capability inventory: The agent possesses powerful write capabilities, including sending messages (DISCORDBOT_CREATE_MESSAGE), managing server roles (DISCORDBOT_CREATE_GUILD_ROLE, DISCORDBOT_ADD_GUILD_MEMBER_ROLE), and executing webhooks (DISCORDBOT_EXECUTE_WEBHOOK).
  • Sanitization: There are no documented procedures for sanitizing or validating external input before it is used in subsequent tool calls or prompt responses.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add a remote endpoint (https://rube.app/mcp) as an MCP server configuration. While this is a common integration pattern, it establishes a dependency on infrastructure outside of the platform's trusted environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 09:15 AM
Security Audit — agent-trust-hub — discord-automation