better-chatbot

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly loads and executes external tools that fetch and return open-web or user-provided content—e.g., APP_DEFAULT_TOOL_KIT includes WebSearch/WebContent, Tier‑1 MCP tools (examples: @mcp("github"), @mcp("slack")), and workflow Http nodes—so the agent will ingest and interpret untrusted third‑party web/social/tool outputs at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:49 PM