skill-publisher@0.1.0
VERIFIED· install onlyPublisher claims: "Publish Agent Skills to clawhub.ai and skills.sh in one workflow. Use when the user wants to release, publish, ship, or distribute a SKILL.md-based skill — even if they don't say "publisher" explicitly. Triggers on phrases like "publish my skill", "release to clawhub", "submit to skills.sh", "发布skill", "上传skill", "上架skill", "ship to marketplace", "make my skill available", "auto-release", or any request to push a skill folder to multiple marketplaces. Generates bilingual README, strips dot-files and credentials, drafts a release note, optionally invokes /skill-optimizer for description tweaks and /release-skill for version bumps." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
- "Push to skills.sh" / "make `npx skills add` work"Fix: Pin versions and sources; vendor anything fetched at install time.- **Credentials in the bundle** — The single biggest risk. `strip_bundle.py` warns on `.env`, `*.key`, `*.pem`, etc., but you must inspect the bundle tree before publishing.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `.env`, `.env.*`, `*.key`, `*.pem`, `credentials.*`, `secrets.*` — any file that smells like credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Do not execute `openclaw skills install` or `npx skills add`.Fix: Pin versions and sources; vendor anything fetched at install time.npx skills add https://github.com/mebusw/<slug>Fix: Pin versions and sources; vendor anything fetched at install time.- `references/skills-sh-publish.md` — How `npx skills add` resolves a repo, what files it scans, and how to debug a failed publish.Fix: Pin versions and sources; vendor anything fetched at install time.npx skills add https://github.com/mebusw/<slug>Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.