SKILLEMALL.ai
GitHub ↗ RU Sign in

CC chrome-ai-action-skill

Browser automation via Chrome AI Action (CAA) bridge. Control Chrome programmatically — navigate, click, type, screenshot, extract content, and more. Uses Puppeteer (CDP) mode. First use auto-installs npm package and starts the bridge. Chrome is auto-launched if not running.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Jami-Lin v1.0.0 MIT-0 5 files · 1 script body ≈ 1 951 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Browser automation via Chrome AI Action (CAA) bridge.

As a process C 63/100 · Has gaps — weak spots: when it triggers, consistency, progress reporting

ProcedurePlaywrightSoftware developmenttype 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
86/100
safety, quality, tests
Safety 60%
82
Quality 40%
92
Run on models
none yet
Process rating
C
63/100
Has gaps
Progress reporting w 2
0
When it triggers w 12
20
Consistency w 8
40
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.

Exfiltration
If you install

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".

For the author

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

  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.
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 · 1

  • high Exfiltration intent-browser-credential-store skill-card.md:51
    Accesses a browser credential / cookie store
    **Other Properties Related to Output:** [May start a local bridge on 127.0.0.1 and produce browser automation requests for navigation, interaction, screenshots, extraction, storage, cookies, network c

Files scanned: 5. 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 63/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (chrome-ai-action-skill) differs from the folder (chromeskill)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 18 steps
  • 100Execution cost. Instruction body is 1951 tokens
  • 100Running it twice. Mutating operations check current state
  • low 10 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)
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 275: enough signal without eating the budget
  • +4Structure: 39 headings
  • +3Step-by-step instructions: 18 items
  • +3Output format is stated explicitly
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

External checks

ClawHub: suspicious
This is a real browser automation skill, but it needs Review because it automatically installs and runs mutable third-party code while giving an agent broad control over Chrome and browser data.
LLM: suspicious (high) · VirusTotal: · 16 Sept 2026