DB 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.
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
As a process B 70/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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.
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".
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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-urlSKILL.md:321Webhook / callback URL commonly used for exfiltration (verify the destination)# → url: https://abc.trycloudflare.com
-
high Exfiltration
exfil-webhook-urlSKILL.md:324Webhook / callback URL commonly used for exfiltration (verify the destination)browser-use --browser remote open https://abc.trycloudflare.com
-
high Exfiltration
intent-browser-credential-storeSKILL.md:369Accesses a browser credential / cookie store**Note:** Cloud profile cookies can expire over time. If authentication fails, re-sync cookies from the local Chrome profile.
-
high Exfiltration
intent-browser-credential-storeSKILL.md:373Accesses a browser credential / cookie storeIf the user wants to use a cloud browser but no cloud profile has the right cookies, sync them from a local Chrome profile.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5594 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 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
- 70Execution cost. Instruction body is 5594 tokens
- 85Steps. 29 steps, 3 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 10 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
- +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: 38 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (36 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.