llama-index

Warn

Audited by Snyk on May 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.md explicitly shows ingesting external data via custom connectors (e.g., CustomDataReader.load_data("api://endpoint") and references "multiple data connectors (300+)") to build indexes that are wrapped by QueryEngineTool and used by agents (search_knowledge / ReActAgent), so arbitrary/untrusted third‑party content can be read and materially influence agent decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 6, 2026, 08:54 AM
Issues
1
Security Audit — snyk — llama-index