BD browser-use-agent
Browser-Use：把 LLM 变成网页操作员的异步 Python 库（Python 3.11+）。Agent 步循环采集 DOM + 截图 → LLM 一次调用产出 thinking / evaluation / next_goal / action[] → 经 CDP 执行。 Browser-Use: an async Python library (3.11+) that turns an LLM into a web operator. The Agent loop collects DOM + screenshot, makes one LLM call emitting thinking / evaluation / next_goal / action[], and executes via CDP. Built on cdp-use; no Playwright.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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.
- 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 Instruction override
en-ignore-previousreferences/seed.yaml:701Instruction-override phrase ("ignore previous instructions")action: If you override the system prompt, KEEP the syst…:71 sentence verbatim ('Only use indexes that are
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 43/100
- 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. 2 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 360 tokens
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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 397: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 7 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.