knowledge-graph-construction

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a set of instructional templates for data modeling and knowledge graph construction. It uses standard, well-known Python libraries (openai, spacy, neo4j, networkx) for their intended purposes.
  • [CREDENTIALS_UNSAFE]: The code correctly handles sensitive configuration by using parameters for database connections (uri, user, password) and relying on standard client initialization for OpenAI, avoiding hardcoded secrets.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates processing external research abstracts through an LLM. While this is an attack surface, the template utilizes structured output formats (json_object) and clear role definitions, which are standard safety practices for extraction tasks.
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation and repositories for well-known services like Neo4j, NetworkX, and OpenAlex. These are informative links to trusted technology platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 02:38 PM