ontology-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is focused on legitimate data engineering and semantic modeling tasks. It provides templates for using established tools like Protege, Neo4j, and Amazon Neptune, and standard libraries for Python and Java.
- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized network operations were detected in the instructions or reference files. External references point to well-known community resources and repositories in the semantic web domain.
- [INDIRECT_PROMPT_INJECTION]: The skill performs data ingestion and information extraction, which constitutes an indirect prompt injection surface.
- Ingestion points: Processes structured (SQL, APIs), semi-structured (JSON, XML), and unstructured (text) sources as defined in
SKILL.mdandreferences/knowledge_graphs.md. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore commands within the source text in its extraction templates.
- Capability inventory: Provides patterns for entity extraction using NLP models and loading data into triple stores using Python and SPARQL.
- Sanitization: There are no explicit sanitization steps for the ingested data before it is processed by the agent models.
Audit Metadata