BD remote-browser-deploy
一键部署远程可视化浏览器：Linux（云服务器/NAS/本地）noVNC + Chromium + CDP 三合一，Windows 本机 Edge/Chrome CDP 一键接管。技术栈：noVNC（Web VNC）+ Chromium（浏览器）+ CDP（Chrome DevTools Protocol）。解决 Headless 浏览器自动化中登录、验证码、滑块等需要人工介入的场景。
一键部署远程可视化浏览器：Linux（云服务器/NAS/本地）noVNC + Chromium + CDP 三合一，Windows 本机 Edge/Chrome CDP 一键接管。技术栈：noVNC（Web VNC）+ Chromium（浏览器）+ CDP（Chrome DevTools Protocol）。解决…
As a process D 44/100 · 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.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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-privilegeSKILL.md:119Privilege escalation / world-writable permissionsecho "$(whoami) ALL=(ALL) NOPASSWD: ALL" | sudo tee /etc/sudoers.d/hermes-deploy
-
medium Dangerous commands
cmd-privilegeSKILL.md:120Privilege escalation / world-writable permissions# 部署完成后执行 sudo rm /etc/sudoers.d/hermes-deploy 收回权限
-
low Dangerous commands
cmd-background-processSKILL.md:362Starts a background / autostarted processsystemctl enable --now xvfb.service x11v…ice novnc.service chromium-remote.service
Files scanned: 2. 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")
Process rating: all ten parameters 44/100
- 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
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4313 tokens
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 194: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (38 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.