discord-bot
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill outlines a blueprint for an AI-powered chat bot and a summarization feature that processes external, untrusted user data from Discord messages and channel history.
- Ingestion points: The bot is designed to trigger on user mentions, direct messages, and through the
/summarizecommand which reads recent channel history (SKILL.md). - Boundary markers: The provided system prompt template does not include explicit delimiters or instructions to ignore potential commands embedded in user messages.
- Capability inventory: The skill utilizes MCP tools for sending messages, creating channels, and managing roles (
discord_send_message,discord_create_channel,discord_manage_roles). - Sanitization: No specific sanitization or filtering logic is prescribed for the data passed to the AI model before processing.
Audit Metadata