Ontology 1

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

This skill appears coherent and implements a local ontology stored under memory/ontology/graph.jsonl using the bundled Python script. It does not request secrets or network access. Before installing: (1) be aware data is persisted locally in the workspace (append-only), so do not store raw secrets or sensitive file contents in entity properties; use secret_ref patterns as recommended; (2) confirm the agent's workspace root is appropriate (the script constrains paths to the workspace); (3) if you intend to expose this graph to other skills, review those skills' permissions because they may read/write the same files; and (4) you may review the full scripts/ontology.py to confirm its behavior matches your expectations (no network or unexpected system access was observed).

Type: OpenClaw Skill Name: ontology-1 Version: 1.0.4 The 'ontology' skill bundle provides a structured knowledge graph system for agent memory with robust security-conscious design. The core script (scripts/ontology.py) includes path traversal protection via a path resolution utility and explicitly implements validation logic to forbid the storage of sensitive credentials like passwords or tokens. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions and code are strictly aligned with the stated purpose of managing entities and relations.