discord
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing external, untrusted data from Discord users through slash commands, message components, and modals, which creates a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through
interaction.optionsinreferences/frameworks/discord-js/commands.md,interaction.fieldsinreferences/frameworks/discord-js/components.md, and command parameters inreferences/frameworks/discord-py/commands.md. - Boundary markers: The provided code snippets and instructions do not include delimiters or instructions to ignore potential commands embedded within user input.
- Capability inventory: The skill enables significant capabilities including sending messages, executing webhooks (
references/webhooks.md), and administrative actions like banning members (references/frameworks/discord-py/commands.md). - Sanitization: No sanitization, escaping, or validation logic for user-provided strings is demonstrated in the examples.
Audit Metadata