llamaindex

Warn

Audited by Snyk on Feb 16, 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 explicitly references "Agents: Building research agents that browse the web and summarize" and "Data Loaders (LlamaHub) — Connectors for Notion, Slack, Discord, PDF, etc.," indicating it ingests open/public and user-generated third‑party content which the agent would read and interpret as part of RAG workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:31 AM