medxpert-l1-batch-study@1.1.9
VERIFIEDPublisher claims: "Batch deep-reading of a document/knowledge-base corpus via the DSH task bridge and a local qwen3.5:4b model — dispatch to inbox, local LLM reading, recover from outbox, persist structured summaries + a consolidated doubt list. Includes two mandatory fixes (qwen3 think:false, bridge timeout 120s→300s) and auto-retry fallback. 本地大模型 + DSH 任务桥批量精读知识库：投递 inbox → 本地 qwen3 精读 → 回收 outbox → 落盘结构化摘要 + 疑点总表，含两处必做修复（qwen3 thinking 关闭、桥超时 120s→300s）与失败自动重投兜底。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 90/100 (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 deviationsStatic findings
No findings across 462 lines in 6 files.
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.