neo4j-document-import-skill
Warn
Audited by Snyk on May 20, 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 fetches and ingests public third‑party content (e.g., apoc.load.json("https://...") in the APOC JSON Ingestion section, the WebPageLoader example using httpx.get, and the LLM Graph Builder which lists "web pages" and "YouTube transcripts" as supported sources), and that content is then interpreted by an LLM as part of the ingestion pipeline to build/modify the knowledge graph—allowing untrusted web content to materially influence tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata