Security audit
Security checks across malware telemetry and agentic risk
This is mostly a local novel-writing workflow, but it needs review because it under-discloses optional package/model downloads that can execute third-party model code.
Review before installing. Use it only if you want a local, stateful novel-project manager, and avoid the optional model installation commands unless you accept third-party package and model downloads, including remote model code execution via trust_remote_code=True. Check where its project data and caches will be stored, and be aware that generic writing prompts may trigger the workflow.
- **[强制] 核心规划字段保护 + 串行阻断** — `novel_state_manager.py` 对核心字段做 MD5 指纹校验，LLM 不可更新。context_loader 检测上一子结构是否为 completed，否则 HOOK-BLOCK 阻断。串行写入，一次只改一个子结构 - **[强制] 串行阻断** — context_loader 加载子结构上下文时检测上一子结构 state 是否为 completed。若为 pending 则输出 HOOK-BLOCK 并给出 write-sub 修复命令，强制走管道完成标记后才能继续。子结构写作必须串行 - **[必须] 先确认+规划再写作** — 场景配置和大纲必须经用户确认，每章先 `plan-chapter`（含必填 writing_prompt + 情绪 tone + 可选 emotions）→ 因果链验证 → 通过串行阻断检查，才可开始写作 - **[必须] 写作规范** — 每段 ≤200行（自然段落结束），atomic write 逐行 fsync，正文禁止 `L##S##` 标记行（会被阻断） - **[强制] 写作中登记** — 新角色出场时 `novel_state_manager.py add-char`。**plan-chapter 已加硬阻断**：sub_structures 中出现未登记角色名时 HOOK-BLOCK，必须先 add-char 才能写入。 - **[强制] 每章六检 + 自动完结** — 写完所有子结构后 **write-sub 自动触发 finalize-chapter**（不再需手动执行）：章内连通性 → 跨章承诺链 → 风格校验 → 逻辑检查 → **语义检查** → **推理审核** → 聚合硬性问题并阻断。通过后自动推进 phase。 - **[必须] 全文三检** — 全文完成后必须：`novel_fidelity.py`（大纲忠实度）+ `verify-ending`（结尾收束验证）+ `set-phase stage3_ready`
65/65 vendors flagged this skill as clean.
No suspicious patterns detected.
