Skills/ClawHub/medxpert-offline-taskbox

medxpert-offline-taskbox@2.4.9

VERIFIED

Publisher claims: "AI API costs burning you? Run LLMs on low-spec machines — dispatch tasks by day, local models finish them for free at night, even offline. MedXpert Cross-Machine Taskbox: WorkBuddy x DSH (DeepSeek Harness) x local Ollama three-tier collaboration. Batch/repeat/document/sensitive tasks cost zero cloud credits; only complex reasoning goes to the cloud. L1-L5 tiered routing (code-level: add auto-tags + route query), auto-retry on failure, sync-package merge across two machines, zombie-proof resume. Pure Python, zero dependencies, so an old laptop works fine as an execution node. AI 任务太烧钱？低配电脑也能跑大模型——白天派活，晚上回家让本地模型免费跑完，断网也不停。MedXpert 跨机任务箱：WorkBuddy×DSH（DeepSeek Harness）×本地 Ollama 三级协同，批量/重复/文档/敏感任务零云端消耗，复杂推理才上云端。L1-L5 分级路由已代码级实现（add 自动打标 + route 查询）、失败自动重试、同步包双机合并、防僵尸续跑，纯 Python 零依赖即下即用，旧电脑也能当执行节点。模型 API 涨价？跟它无关。省积分、断网续跑、离线任务队列、任务路由与成本控制都找它。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher zhaoxinghua09-cell · joined 10 days agoInstalls 409Last detonated 1 h ago
$clawhub install medxpert-offline-taskbox
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 80/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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 packageSKILL.md:240 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Outbound HTTP to raw IP addressSKILL.md:240 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addressSKILL.md:240 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedoffline_worker.py:42 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addressSKILL.md:243 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addressSKILL.md:243 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈3,963 tok
1 file · 5 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.

medxpert-offline-taskbox@2.4.9 safety verdict: Verified 80/100 — KillerSkills