BF browse-anything
Drive a real Chromium browser with an autonomous AI agent to do anything on the web — book flights, scrape sites, fill forms, log into apps, extract data behind authentication, monitor pages, complete checkout flows. Use whenever the user asks to "browse", "use the web", "look up something live", "do this on <website>", "log in and...", "scrape", "buy", "book", "fill out a form", "screenshot a page", "check a price", or any task that requires actually loading and interacting with web pages instead of guessing from training data. Backed by the hosted BrowseAnything platform (https://browseanything.io).
As a process F 49/100 · Will not run — References files that are not bundled: references/recurring-scraping-pipeline.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- The text references files that are not there: add them or drop the references.
- 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
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/_client.py:44Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/recurring-scraping-pipeline.md
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: references/recurring-scraping-pipeline.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (browse-anything) differs from the folder (browseanything)
- 70When it triggers. States when to use, but not when not to
- 100Steps. 35 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1580 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (6 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)
- +3Output format is not stated: the model decides each time
- -31 of 9 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 608: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.