Automation & Ops security-auditingreputation-checkingsupply-chain-verificationopenclawclawhubrelease-signing

ClawHub Reputation Gate

Checks ClawHub reputation before OpenClaw skill installation and requires explicit approval for low-scoring skills.

FollowSkills review · FSRS-2.0
Not recommended
55/ 100 5-point scale 2.8 / 5
Trust16 / 25 · 3.2/5

The files disclose the node/clawhub/openclaw dependencies, ClawHub network lookups, heuristic trust model, and confirmation flags. They also provide confirmation gating, optional manual hook wiring, signed-manifest/hash verification, and a non-mutating setup helper. Points are deducted because installation is delegated to an external suite without fully specified data flows, permission boundaries, or rollback; --confirm-reputation can bypass the reputation gate entirely, and the verification script downloads remote artifacts and removes a temporary directory.

Reliability8 / 20 · 2.0/5

The source includes input validation, exit codes, exception feedback, and committed tests, making the main reputation path reasonably coherent. Static review cannot establish executability; additionally, --dry-run is parsed but unused, the hook integration hard-codes threshold 70, and documentation contains minor dependency and command inconsistencies. The score therefore remains below the static ceiling.

Adaptability9 / 15 · 3.0/5

The intended scenario, parameters, exit codes, threshold, and trigger phrases are reasonably explicit for pre-install checks on OpenClaw. Points are deducted because the skill requires clawsec-suite, clawhub, node, and openclaw, is not fit for non-OpenClaw users, depends on network access to ClawHub without mainland-China reachability guidance, and provides no Chinese usage documentation.

Convention10 / 15 · 3.3/5

SKILL.md, README, skill.json, and CHANGELOG provide useful layering, installation steps, configuration, examples, limitations, licensing, version history, SBOM data, and manual integration notes. Points are deducted because maintenance ownership, update procedures, and compatibility policy are unclear; publisher identity is not verified by the FollowSkills enterprise registry; and some installation/runtime declarations are inconsistent.

Effectiveness7 / 15 · 2.3/5

The implementation combines ClawHub metadata, author activity, download counts, age, update recency, and scanner results, and requests explicit confirmation for low scores. Committed tests cover several validation cases and a malicious VirusTotal case. Static review cannot verify real outputs or network compatibility; heuristics may produce false positives or negatives, and --confirm-reputation bypasses the check, so the score is capped at the static maximum.

Verifiability5 / 10 · 2.5/5

The source provides implementation code, a skill.json SBOM, changelog entries, signed-release verification instructions, and committed tests, enabling limited auditing. Points are deducted because tests were not executed in this review, the tests mock ClawHub rather than corroborating behavior against the real service, and there is no independent third-party review or execution evidence; under the static rules the score cannot exceed 5.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision eac8392f8ac9
Before you use it
  • Do not treat the heuristic reputation score as proof of safety; manually review the target skill before using --confirm-reputation.
  • Reputation checks depend on ClawHub inspect/search network endpoints and may block when scanner data is unavailable; mainland-China reachability is not established.
  • --dry-run is parsed but no actual dry-run behavior is shown; advisory-hook integration is manual and should be backed up and reviewed for compatibility.
  • Dependencies and suite-version compatibility were not executed or independently verified in this static review.
See the full review method →

What does this skill do, and when should you use it?

ClawHub Reputation Gate is a standalone ClawSec skill that works with the clawsec-suite guarded installer. It reads ClawHub metadata and scanner results, then applies heuristic signals such as age, update activity, author history, and downloads. Skills below the configured threshold require an explicit --confirm-reputation flag. The package also documents signed release-manifest verification, but it requires local Node.js, clawhub, OpenClaw, and clawsec-suite dependencies.

Reads skill metadata with clawhub inspect --json; evaluates scanner status and includes a VirusTotal summary when available; applies reputation heuristics based on age, updates, author history, and downloads; requires --confirm-reputation below the configured score threshold; runs the enhanced guarded installer; optionally validates local paths and prints a recommended command; downloads and verifies checksums.json, checksums.sig, the signing public key, the archive, SKILL.md, and skill.json to validate the signed manifest, public-key fingerprint, and SHA-256 hashes.

  1. An OpenClaw administrator wants a reputation gate before installing third-party skills through the guarded installer.
  2. A team installing skills from ClawHub wants scanner status and reputation signals included in its approval process.
  3. An operator evaluating a new or low-reputation skill wants an explicit confirmation step before proceeding.
  4. A maintainer installing a standalone release archive wants to verify its signed manifest before trusting or extracting package files.

What are this skill's strengths and limitations?

Pros
  • Adds a separate reputation gate to the guarded installer.
  • Combines scanner status, an available VirusTotal summary, age, update activity, author history, and downloads.
  • Provides signed-manifest, public-key fingerprint, and SHA-256 verification steps.
  • Does not rewrite files belonging to other installed skills, according to the operational notes.
Limitations
  • Requires clawsec-suite plus node, clawhub, and openclaw.
  • Reputation scores are heuristic, and scanner results may have false positives or false negatives.
  • Reputation checks call ClawHub inspect/search endpoints over the network.
  • Advisory hooks are not patched automatically; the source does not provide test-coverage or cost information.

How do you install this skill?

Install the dependency first: npx clawhub@latest install clawsec-suite. Then install this skill: npx clawhub@latest install clawsec-clawhub-checker. For the Vercel Skills CLI, use: npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a openclaw -y. For standalone releases, run the supplied verification procedure successfully before trusting or extracting the archive.

How do you use this skill?

Run: node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/enhanced_guarded_install.mjs --skill some-skill --version 1.0.0. If the score is below threshold, rerun with --confirm-reputation only after review. An optional preflight is: node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/setup_reputation_hook.mjs. The default threshold is 70 and can be changed with CLAWHUB_REPUTATION_THRESHOLD. Advisory-hook wiring is manual in this release.

FAQ

Does it automatically block every low-reputation skill?
A score below the threshold requires the explicit --confirm-reputation flag. This is a confirmation gate, not an absolute safety guarantee.
Does the package modify other installed skills?
Its operational notes say it does not rewrite installed suite files. Optional advisory-hook wiring is a separate manual customization.
What do the exit codes mean?
0 means safe to install, 42 means advisory confirmation is required from clawsec-suite, 43 means reputation confirmation is required, and 1 indicates an error.
Does it require network access?
Yes. Reputation checks call ClawHub inspect/search endpoints, and release verification downloads files from GitHub Releases.

More skills from this repository

All from prompt-security/clawsec

Automation & Ops

Picoclaw Security Guardian

A read-first security layer for Picoclaw advisory checks, configuration drift detection, and signed release verification.

Automation & Ops

ClawSec Suite Manager

Protect OpenClaw skill installs with signed advisories, risk checks, and approval-gated responses.

Automation & Ops

OpenClaw Audit Watchdog

Automates daily OpenClaw security audits and delivers actionable reports.

Automation & Ops

Soul Guardian File Integrity Guard

Detect and handle unauthorized changes to an agent’s core workspace files.

Automation & Ops

OpenClaw Traffic Guardian

A scoped, opt-in runtime traffic monitoring baseline for OpenClaw.

Automation & Ops

ClawSec Advisory Feed

Keep OpenClaw agents informed about emerging security threats.

Automation & Ops

ClawSec Scanner

Unify dependency, CVE, source-code, and OpenClaw hook risk scanning in one agent-security workflow.

Automation & Ops

ClawSec Release Manager

A maintainer workflow for versioning, releasing, and verifying Claw skills through GitHub.

Automation & Ops

Hermes Attestation Guardian

Generate verifiable Hermes security attestations and detect authenticated baseline drift.

Automation & Ops

NanoClaw Security Sentinel

Check NanoClaw skills for known risks before installation and during operation.

Automation & Ops

Picoclaw Traffic Guardian

An opt-in, detect-and-log baseline for monitoring Picoclaw gateway traffic and exporting security posture data.

Automation & Ops

Picoclaw Security Posture Review

Review Picoclaw security posture in read-only mode and give operators safe remediation guidance.

Automation & Ops

NanoClaw Traffic Guardian

A host-managed baseline for optional NanoClaw traffic inspection and runtime security findings.

Automation & Ops

Hermes Traffic Guardian

A consent-based, auditable baseline for monitoring Hermes runtime traffic.

Automation & Ops

Clawtributor Security Reporter

Prepare sanitized AI-agent incident reports for explicit human approval before submission.

Related skills