discord-server

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from Discord messages, which serves as an ingestion point for indirect prompt injection attacks.
  • Ingestion points: The commands/read-messages.mjs script (line 50) fetches and returns the content of messages from Discord channels.
  • Boundary markers: Although the output is structured as JSON, there are no explicit boundary markers or instructions to the agent to treat the message content as data only and ignore any embedded commands.
  • Capability inventory: The skill provides extensive management capabilities, including destructive actions like deleting channels and roles (commands/delete-channel.mjs, commands/delete-role.mjs) and modification of server settings.
  • Sanitization: The message content is included in the JSON output exactly as received from the Discord API without sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 11:58 PM
Security Audit — agent-trust-hub — discord-server