discord

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs the agent to call Discord API endpoints ("Get Channel ID" and "Get User ID" sections) which fetch guild channels and members — untrusted, user-generated data from discord.com that the agent is expected to read and use to choose targets for follow-up send-message actions, so third-party content could influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 07:49 AM