SKILLEMALL.ai
GitHub ↗ RU Sign in

CC page-agent-browser

通过 page-agent CLI（CDP）驱动浏览器；CLI 当前仅从 GitHub Release 的 .tgz 安装（npm 官方包尚未发布）。

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Yuesen v1.0.0 MIT-0 7 files body ≈ 1 596 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGitHubAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
67/100
safety, quality, tests
Safety 60%
67
Quality 40%
67
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

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.

Dangerous commands
If you install

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.

For the author

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.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. 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.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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 · 4

  • high Dangerous commands cmd-install-from-url SKILL.md:32
    Installs a package from an untrusted URL / archive
    npm install -g ./page…tgz
Medium and low: 3
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(curl:*)
    allowed-tools: Bash(page-agent:*) Bash(curl:*) Exec(tools:process:kill)
  • medium Dangerous commands cmd-install-from-url SKILL.md:36
    Installs a package from an untrusted URL / archive (quoted — discussed, not commanded)
    无 `gh` 时：在发布页手动下载同名 `.tgz` 后执行 `npm install -g ./page-agent-cli-<version>.tgz`。
    quoted
  • medium Dangerous commands cmd-install-from-url SKILL.md:38
    Installs a package from an untrusted URL / archive (quoted — discussed, not commanded)
    本 monorepo 内开发：`npm pack -w @page-agent/cli` 生成 tgz，再 `npm install -g ./<generated>.tgz`。
    quoted

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

  • 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. 1 mutating operations with no state check
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 8 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1596 tokens
  • low The response is described with custom markup (5 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

  • +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 75: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: suspicious
This is a disclosed browser-automation skill, but it deserves review because it directs users to install an external global CLI and run it against their normal logged-in browser profile.
LLM: suspicious (high) · VirusTotal: · 29 May 2026