DF medical-device-reg-hub
🌐 官网：https://medxpert.cn/knowledge/（医械注册知识库·免费公开层，20+ 枢纽在线可读）。医疗器械注册工程师的「随身资料库」——中国 NMPA / 美国 FDA / 欧盟 MDR / 日本 PMDA 及东南亚·拉美全球注册路径与分类，UDI、STED 技术文件、生物相容性(ISO 10993)、GMP 质量体系、上市后监管、标签与 IFU、供应商合规等 20 个专题枢纽按「全生命周期 7 阶段」（需求立项→分类路径→技术文件→质量体系→注册申报→审评获批→上市后）全覆盖，官方直达链接一站备齐。告别资料散落、少查半天、少踩坑，从立项到拿证全程有底。119 条官方链接已浏览器级逐条核验可达。
🌐 官网：https://medxpert.cn/knowledge/（医械注册知识库·免费公开层，20+ 枢纽在线可读）。医疗器械注册工程师的「随身资料库」——中国 NMPA / 美国 FDA / 欧盟 MDR / 日本 PMDA 及东南亚·拉美全球注册路径与分类，UDI、STED 技术文件、生物相容性(ISO…
As a process F 34/100 · Will not run — References files that are not bundled: assets/overview.svg
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The text references files that are not there: add them or drop the references.
- 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 · 7
-
high Dangerous commands
cmd-pipe-to-shell安全审计报告.md:29Downloads and executes remote code from an unrecognised host (pipe to shell)| 远程脚本下载执行 | 无 curl\|bash、base64 解码执行等模式 | ✅ 无风险 |
Medium and low: 6
-
medium Obfuscation
obf-base64-blobreferences/GMP质量体系与验证枢纽.md:62Long base64-looking blob| FDA 再处理质量影响因素 | [fda.gov Factors Affecting Quality of Reprocessing](https://www.fda.gov/MedicalDevices/ProductsandMedicalProcedures/ReprocessingofReusableMedicalDevices/ucm4…htm) — 复用器械再处理质量影响因
-
medium Obfuscation
obf-base64-blobreferences/上市后监管枢纽.md:62Long base64-looking blob| 2018 年第 1 号令全文（PDF） | [samr.gov.cn 不良事件监测和再评价管理办法 PDF](https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/bgt/202106/W020…pdf) — 2018 年第 1 号令 |
-
medium Obfuscation
obf-base64-blobreferences/变更延续管理枢纽.md:35Long base64-looking blob- [47 号令全文 PDF（市场监管总局）](https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/fgs/202108/W020…pdf)
-
medium Obfuscation
obf-base64-blobreferences/变更延续管理枢纽.md:72Long base64-looking blob| 47 号令全文 | [SAMR PDF](https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/fgs/202108/W020…pdf) | 变更/延续注册章节依据 |
-
medium Obfuscation
obf-base64-blobreferences/审评核查获证枢纽.md:66Long base64-looking blob| 生产监督管理办法（SAMR） | https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/fgs/202203/W020…pdf |
-
medium Obfuscation
obf-base64-blobreferences/注册工程师资料枢纽.md:42Long base64-looking blob- **医疗器械生产监督管理办法 ｜ 生产许可/核查** 【II III】 ⅡⅢ规章[SAMR 公开](https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/fgs/202203/W020…pdf)
Files scanned: 35. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 315 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - warning
missing-refreference to a missing file: assets/overview.svg - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "title" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "xiaping_category" - note
frontmatter-keyunknown frontmatter key "xiaping_tags" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "verified_links"
Process rating: all ten parameters 34/100
- 0Tools and files. 1 referenced file(s) missing: assets/overview.svg
- 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
- 70Execution cost. Instruction body is 4449 tokens
- 100Steps. 107 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 315: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 107 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (27 of 28)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.