Skills/ClawHub/skill-publisher

skill-publisher@1.0.3

VERIFIED· install only

Publisher claims: "将本地技能一键打包、生成中文 PDF 说明文档、发布到 ClawHub,并自动截取发布页截图与链接,形成「创建→发布→文档→留证」的完整闭环。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher zhexin233-ui · publishing for 78 daysInstalls 401Last detonated 6d ago
$clawhub install skill-publisher
WatchReport an issue

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 2026-11-08 and scored it 89/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagescripts/publish.py:107 · npx invocation of non-well-known package — may execute untrusted codestory.append(Paragraph("技能已成功发布,页面可公开访问并可通过 npx claw skills install 安装。", base))Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedscripts/publish.py:359 · Python subprocess execution detectedr1 = subprocess.run([node, ab_js, "open", url],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/publish.py:365 · Python subprocess execution detectedr2 = subprocess.run([node, ab_js, "screenshot", str(out_path)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/publish.py:286 · Python subprocess execution detectedout = subprocess.run([node, "-e",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/publish.py:338 · Python subprocess execution detectedres = subprocess.run(cmd, capture_output=True, text=True, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈638 tok
1 file · 3 in bundle

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.

skill-publisher@1.0.3 safety verdict: Verified (install only) — KillerSkills