medxpert-offline-taskbox@2.4.10
CAUTIONPublisher 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: static analysis only — behavior not yet observed.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-06 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Outbound HTTP to raw IP address. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
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.
What would make this Verified
23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim zhaoxinghua09-cell: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.