SKILLEMALL.ai
GitHub ↗ RU Sign in

CB browser-use

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: shawn pana v2.0.1 MIT-0 4 files body ≈ 2 315 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

As a process B 74/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting

ProcedureGitHubAI and agentstype 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
74/100
safety, quality, tests
Safety 60%
71
Quality 40%
88
Run on models
53
No improvement model run: 64% with skill · 52% without
Process rating
B
74/100
Nearly there
Result and completion w 14
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: browser-use (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.
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 Exfiltration exfil-webhook-url SKILL.md:169
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    browser-use open https://abc.trycloudflare.com     # Browse the tunnel
Medium and low: 3
  • medium Exfiltration intent-browser-credential-store SKILL.md:29
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    To use the user's existing Chrome (preserves logins/cookies): run `browser-use connect` first.
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:168
    Webhook / callback URL commonly used for exfiltration (verify the destination) (code comment)
    browser-use tunnel 3000                            # → https://abc.trycloudflare.com
    comment
  • low Exfiltration intent-browser-credential-store SKILL.md:38
    Accesses a browser credential / cookie store (code comment; quoted — discussed, not commanded)
    browser-use connect                            # Connect to user's Chrome (preserves logins/cookies)
    commentquoted

Files scanned: 4. 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 74/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 17 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2315 tokens
  • low 15 top-level sections: this looks like several domains in one skill
  • 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

  • +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
  • +1No license
  • +2Single-language instructions
  • +3Description length 235: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

Model run · 10 Sept 2026

With the skill
64%
+12 pp vs baseline
Without the skill (baseline)
52%
triggers: +100% / −100%

No improvement Pass rate 64% is below threshold 80% · 7 cases · $0.051

External checks

ClawHub: suspicious
This browser automation skill is mostly coherent, but it gives agents several sensitive powers that are not clearly warned about or scoped for users.
LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026