trust-verifier

Analyze ClawHub skill publisher history, version history, and dependency chains to generate trust scores and attestations.

Updated Mar 4, 2026
One-click install
npx skills add https://github.com/velamints2/clawbot-lab --skill trust-verifier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trust-verifier
Source: https://github.com/velamints2/clawbot-lab/tree/main/skills/arc-trust-verifier
Command: npx skills add https://github.com/velamints2/clawbot-lab --skill trust-verifier

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Trust verification for ClawHub skills: it analyzes publisher history, version consistency, and dependency chains, and generates attestations to improve security and provenance.

Core Features & Use Cases

  • Assess a skill directory for trust signals and compute a confidence score.
  • Generate attestations that capture a skill's integrity for auditing.
  • Verify existing attestations against current skill contents and detect changes.
  • Inspect dependency trust chains to surface untrusted or missing components.

Quick Start

Run the trust verifier against a skill directory to assess trust and produce an attestation.

Frequently Asked Questions about trust-verifier

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify the trustworthiness of a skill before installing it?

To verify skill trustworthiness, you can run a trust verifier against the skill directory to analyze publisher history, version consistency, and dependency chains, producing a confidence score.

How do I generate an attestation for a skill's integrity for auditing?

Generating an attestation involves running the trust verifier on the skill directory, which validates SKILL.md frontmatter, hashes skill contents, and produces an attestation capturing the skill's integrity.

How do I detect changes in a skill using an existing attestation?

To detect changes in a skill using an existing attestation, you verify the attestation against current skill contents, allowing you to identify any unauthorized modifications since the attestation was generated.

How do I inspect dependency trust chains to find untrusted components?

Inspecting dependency trust chains involves analyzing the skill's dependencies to surface untrusted or missing components, ensuring the entire dependency tree meets your security evaluation requirements.

What skill metadata is validated during trust verification?

During trust verification, the system validates SKILL.md frontmatter, hashes the skill contents, and assesses publisher history to compute an overall trust score and generate provenance attestations.