neo4j-import-skill

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to ingest remote public content (e.g., "https://example.com/data.csv" in File Path Rules and "Source is JSON/API → apoc.load.json" in the decision tree), so the agent will read and act on untrusted third‑party data as part of its import workflow.