Ontology To Expertpack

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Installing or enabling the skill may request wallet-related authority that is not needed for a local file conversion workflow.

Why it was flagged

Wallet-related authority is sensitive and not explained by the converter's stated purpose or visible code, which only reads a graph file and writes local ExpertPack files.

Skill content
Capability signals: - requires-wallet ... Primary credential: none
Recommendation

Do not grant wallet access unless the publisher clearly documents why it is required; the publisher should remove or justify this capability signal.

What this means

Private notes, business details, or prompt-like content already present in the ontology graph can become persistent ExpertPack content and may later be retrieved by agents.

Why it was flagged

The script copies ontology entity properties into generated Markdown files, filtering only property names that look credential-like.

Skill content
props = sanitize_properties(entity.get('properties', {})) ... md.append(f"- **{k}:** {v}")
Recommendation

Run it only on a graph you intend to migrate, inspect the generated pack for sensitive or untrusted content, and remove secrets before using or sharing it.

What this means

If the generated pack contains private or incorrect information, committing or uploading it could spread that content to other tools or users.

Why it was flagged

The sharing step is user-directed and preceded by review guidance, but it can propagate exported ontology memory beyond the local machine.

Skill content
Commit to git and share via expertpack.ai or ClawHub
Recommendation

Review and sanitize the output before committing it to git or sharing it through any external service.