discord-agent

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's Deep-Thinking Rule explicitly requires using Brave Search / Tavily for research (see ".cursor/rules/deep-thinking.mdc"), which fetches and ingests public web content that the agent will read and use to drive decisions and reports, exposing it to untrusted third‑party content that could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 05:30 PM