AC url2pdf-mk
EN: Webpage to PDF + Markdown converter. Converts any URL (especially WeChat articles) into offline-readable PDF and Markdown files with complete images, preserving original layout and styles. Auto-creates date-named folders on desktop, filenames use publish date + title. ⚠️ Security Note: Browser mode (default) reuses your Chrome profile — it can access your cookies and logged-in sessions. Use --isolated for public content, or run in a VM/sandbox. CDP proxy opens a local port and writes temp state files (cdp-proxy-<user> in your temp directory). 微信文章 / 网页抓取工具，将任意 URL 输出为含完整图片的 PDF 和 Markdown 文件。 自动在桌面按当前日期创建目录，文件名使用文章发布日期 + 标题。 当用户提到"网页转 PDF"、"保存微信文章"、"抓取网页内容"、"导出 PDF 和 Markdown"、 "url2pdf"、"网页保存"、"url2pdf-mk"、"保存链接"、"离线阅读"、"网页存档"、"批量抓取"等时触发此技能。
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, progress reporting
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 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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
intent-browser-credential-storeSKILL.md:228Accesses a browser credential / cookie store (documentation of a security skill)| Profile reuse / Profile 复用 | Can access Chrome cookies/login sessions / 可访问 Chrome Cookie/登录态 | ✅ Always use `--isolated` for public content / 公开内容一律用 `--isolated` |
security skill -
low Dangerous commands
cmd-background-processscripts/cdp_proxy.py:653Starts a background / autostarted processos.setsid()
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4043 tokens
- 100Steps. 85 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -232 emoji in the instructions: noise for the model
- -35 of 10 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 757: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 85 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.