skills/openhands/extensions/discord/Gen Agent Trust Hub

discord

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the standard requests library to communicate with the official Discord API at discord.com. This is necessary for the skill's primary function and targets a well-known service.
  • [CREDENTIALS_UNSAFE]: The skill handles sensitive secrets (Bot Tokens and Webhook URLs) securely. It avoids hardcoding by utilizing environment variables (DISCORD_WEBHOOK_URL, DISCORD_BOT_TOKEN) and includes specific logic in scripts/_http.py and scripts/post_webhook.py to redact tokens from URLs in error messages to prevent leakage in log files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content to be posted to Discord. To prevent exploitation through mass pings or role mentions, the scripts default to a strict allowed_mentions policy ({"parse": []}), which effectively mitigates common injection risks associated with Discord automation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 06:31 PM