japanese-conversation-scorer@1.1.7
VERIFIED· install onlyPublisher claims: "面向 A1/A2/B1（对应 JLPT‑N5~N3）师生对话场景的日语口语批改 Skill。基于 faster‑whisper 完成音频 ASR 转写，采用 ** 内容完整性 50%、准确性 20%、流利度 30%** 三维加权预评分，秉持鼓励优先原则，降低语法偏差对总分的拖累。内置专有名词白名单，防止人名、地名被 AI 误判扣分；设置 ASR 置信度分级，低置信场景下 AI 分数仅作后台参考，交由教师人工打分。生成老师详细版、学生简洁版两套反馈，支持 CSV 批量导出。本技能平台无关，对接 LMS 需自行开发适配器；AI 仅做预批改，全部错误必须经过教师复核确认，不会自动判错扣分。" 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 2026-11-08 and scored it 93/100 (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
No findings across 465 lines in 2 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.