DD wps-office-suite
WPS Office 全家桶 - 四引擎（WPS/MS Office/LibreOffice/纯Python）智能识别用户已安装软件，纯Python模式支持排序/筛选/图表/公式/统计，含文档模板（代码生成）、最佳实践案例、故障排除大章（20+避坑+15 FAQ+15错误ID 统一索引）、自动重试、硬件自适应、环境自检、Skill更新提醒；v5.1新增：kingdoc云端桥接（白名单探测+配置预检+subprocess上传+差异检查）、条件格式/数据验证跨引擎IO（JSON中间格式保真往返）、会议纪要三段式要素化（待办清单+决策记录+风险异议）+说话人标注（MFCC聚类）；v5.2新增：公文一键排版（GB/T 9704 规则库约束+结构识别套版+红头预留位+联合行文）、批量水印与敏感信息打码（身份证/手机号/银行卡/邮箱双轨识别+黑色矩形覆盖+打码清单）、跨文档知识检索与问答（本地TF-IDF零依赖+跳转+可选zwjh记忆桥接）；删除：与contract-review重复的轻量合同审查模块，改为文档互链引导；v5.2.5修复：MS Office引擎下Excel/PPT创建必然失败（错用Word COM对象），新增get_ms_excel/get_ms_ppt及三槽位统一释放release_ms，MS Office路径透传filepath参数;v5.3.0新增：统一CLI入口 wps（registry.json注册表分发，office --app/--action 与 convert 子命令、--list 一屏列出全部命令，薄路由层不改脚本内部逻辑）、全命令 --json 机器可读输出（固定 ok/error_id/elapsed/data 四字段，对齐 E001-E015，wps_error.py 新增 emit_json 统一出口）、_worker 启动优化（wps_pure 改惰性加载，pywin32/python-docx/openpyxl 经核查已惰性导入，ENGINE_CACHE 进程级单例复用，COM 释放统一走 release_ms 三槽位）、转换三入口合并为 convert（format_converter/md_converter/wps_docx_to_ppt 内部按目标格式路由，旧脚本保留为兼容别名并提示新命令，v6.0.0 移除）
WPS Office 全家桶 - 四引擎（WPS/MS Office/LibreOffice/纯Python）智能识别用户已安装软件，纯Python模式支持排序/筛选/图表/公式/统计，含文档模板（代码生成）、最佳实践案例、故障排除大章（20+避坑+15 FAQ+15错误ID…
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-eval-dynamicscripts/doc_search.py:296Dynamic code execution from decoded/untrusted inputos.startfile(top["file"]) if sys.platform == "win32" else os.system(f'xdg-open "{top["file"]}"') -
medium Exfiltration
net-redirectable-api-keyscripts/document_translator.py:124Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/meeting_minutes.py:573Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 57. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5781 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 42/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5781 tokens
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- low 15 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 994: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2168 emoji in the instructions: noise for the model
- -37 of 48 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 64 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (32 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.