learning-english-from-tv-series@1.0.0
CAUTION· static onlyPublisher claims: "看剧/看电影学英语的完整闭环学习引擎（别名 DramaLex），面向中文母语者。agent 用自身联网能力自主检索并解析公开字幕，再围绕这一集/这部电影产出完整学习闭环——学前 CEFR 水平诊断、目标词汇预热、听力理解、字幕精读与语言点标注（语法/搭配/篇章/发音）、口语跟读与角色扮演、写作改写续写并给反馈、跨集/跨技能间隔复现。产物覆盖 4 份结构化 CORE JSON（words/listening/annotated/tasks）与 5 种可交付格式（HTML 学习页 / Anki 卡片 / Excel 词表 / Word 文档 / Markdown）" Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Hidden zero-width characters detected; Hidden zero-width characters detected. 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
ws.append([f"👨💻 {AUTHOR} · {CONTACT}"])Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.<b>👨💻 yinjianheng（殷健恒）</b> | Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.> 👨💻 **作者**：yinjianheng（殷健恒） · GitHub：[@yinjianheng](https://github.com/yinjianheng)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.--known-lines known.txt --output subtitle.srt --parse-out subtitle.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.r = subprocess.run(['say', '-v', voice, '-o', aiff, text], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.rc = subprocess.run(['afconvert', '-f', 'WAVE', '-d', 'LEI16', aiff, out_wav], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.print(f"\n👨💻 {AUTHOR} · [email protected] · WeChat: YJH-yinjianheng")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.r = subprocess.run([exe, '--stdout', '-w', out_wav, text], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.f"👨💻 {AUTHOR} · [email protected] · WeChat: YJH-yinjianheng · GitHub: yinjianheng",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.return subprocess.run([sys.executable, os.path.join(HERE, py), *a])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.lines += [f"> 👨💻 {AUTHOR} · {CONTACT}", f"> {LEGAL}"]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.doc.add_paragraph("👨💻 yinjianheng（殷健恒） · [email protected] · WeChat: YJH-yinjianheng").runs[0].font.size = Pt(9)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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
21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim yinjianheng: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.