ClawHub

Fox Ontology

v1.0.0

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

⭐ 0· 57·2 current·2 all-time
by@tihuaqin-commits
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (typed knowledge graph for agent memory) match the provided SKILL.md and the included Python script: all operations (create/query/relate/validate) operate on a local JSONL graph and schema files. There are no unrelated required binaries or environment variables.
✓
Instruction Scope
Runtime instructions operate on local storage (memory/ontology/graph.jsonl and schema.yaml) and describe entity CRUD, validation, and graph-based planning. The SKILL.md does not instruct the agent to read arbitrary system files or exfiltrate data. It recommends referencing secrets via secret_ref rather than storing secrets in plain properties; however this is guidance only (no external secret integration is implemented).
✓
Install Mechanism
No install specification present (instruction-only with a script file). Nothing is downloaded or executed from external URLs and no package managers are invoked.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. Example schema fields reference secret references (e.g., keychain:github-token) but the skill does not request or manage those secrets itself.
✓
Persistence & Privilege
The skill is not force-installed (always:false) and does not request elevated platform privileges. It writes data to a workspace-local path (memory/ontology/graph.jsonl) which is appropriate for a local ontology; the included resolve_safe_path helper enforces staying inside the workspace root (reduces risk of path traversal).
Assessment
This skill appears internally consistent and implements a local, append-only ontology stored under memory/ontology/graph.jsonl. Before installing/use: (1) review the full scripts/ontology.py to confirm the truncated portions match the same local-only behavior; (2) be careful not to store raw secrets in entity properties—use secret_ref patterns and your own secret store instead (the skill only documents that practice; it does not enforce external secret storage); (3) note the skill writes files under your workspace (memory/ontology); if that is sensitive, choose a secure location or restrict access; (4) there is a small metadata mismatch in the bundled _meta.json ownerId vs the registry owner id—likely benign but worth noting. Overall the skill is coherent with its stated purpose.

Like a lobster shell, security has layers — review code before you run it.

latestvk97efer191x8xc1j5rtdab3x5h83tnmw

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments