Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Removed internal file paths. Public-safe release.
What This Skill Does
On-chain provenance registry for agent skills on Solana. Lets you check a skill's trust level, register new skills with a content hash, submit audit verdicts, and add community vouches before installation.
Unlike manual code review alone, this ties skill identity to an immutable on-chain record so tampering or version drift is detectable via hash mismatch.
When to use it
- Checking a third-party skill's trust badge before installing it
- Registering a locally developed skill with a verifiable on-chain hash
- Submitting a security audit verdict for a community skill
- Vouching for a trusted skill with a score
- Looking up the full audit and vouch history for any registered skill
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: check if the skill 'data-exfil-helper' is safe to install
- 1Call checkSkill with the skill ID against the Solana RPC
- 2Read skill_registry, skill_audits, and skill_vouches tables
- 3Compute trust level from audit severity verdicts
- 4Compare local content hash against registered short hash
- 5Return trust badge, author, version, audit history, and vouch count
Trust badge: FLAGGED — 1 high-severity audit, 2 vouches, hash matches registered version
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.