discord-bot-architect
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides code templates for building Discord bots that ingest untrusted user input via slash commands, buttons, select menus, and modals. The 'Deferred Response Pattern' section includes examples (e.g.,
callOpenAI(result)) where this data is passed to LLMs, establishing a surface for indirect prompt injection. Ingestion points include interaction handlers in the provided Node.js and Python code. The templates lack boundary markers and sanitization logic for data passed to LLMs. - [DYNAMIC_EXECUTION]: The Node.js boilerplate uses fs.readdirSync and require() to dynamically load command files from the local filesystem, which is a standard pattern for modular Discord bot development.
- [SAFE]: The documentation explicitly warns against bot token exposure, recommends using .env files for secret management, and provides code using environment variables. It also advises developers to follow the principle of least privilege regarding Gateway intents.
Audit Metadata