SKILLEMALL.ai
RU Sign in

CC agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: chulla-ceja v0.1.0 MIT-0 12 files · 3 scripts body ≈ 5 968 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 64/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

IntegrationAI 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
71/100
safety, quality, tests
Safety 60%
63
Quality 40%
84
Run on models
none yet
Process rating
C
64/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: agent-browser (ClawHub)

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.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 3

  • high Exfiltration intent-browser-credential-store references/authentication.md:24
    Accesses a browser credential / cookie store
    The fastest way to authenticate is to reuse cookies from a Chrome session you are already logged into.
  • high Exfiltration intent-browser-credential-store references/authentication.md:41
    Accesses a browser credential / cookie store
    > **Security note:** `--remote-debugging-port` exposes full browser control on localhost. Any local process can connect and read cookies, execute JS, etc. Only use on trusted machines and close Chrome
Medium and low: 1
  • low Exfiltration net-credential-use SKILL.md:89
    Credential used in a network call (verify the destination is the intended service) (security demo / example; quoted — discussed, not commanded)
    echo "$PASSWORD" | agent-browser auth save myapp --url https://app.example.com/login --username user --password-stdin
    demoquoted

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5968 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 64/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (agent-browser) differs from the folder (agent-browser-6)
  • 60Result and completion. Output format stated, no completion criterion
  • 60Failures and branches. 2 branches
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5968 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 16 steps
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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)
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 8 example trigger phrases
  • +3Description length 488: enough signal without eating the budget
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 16 items
  • +3Output format is stated explicitly
  • +4Has examples (38 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: suspicious
This appears to be a legitimate browser automation skill, but it grants broad browser, session, credential-adjacent, and persistence capabilities with weak default containment.
LLM: suspicious (high) · VirusTotal: · 29 May 2026