FC browser-cli
(no description)
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
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.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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.
- Add a description to the frontmatter: without it the skill never triggers.
- 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 · 8
-
high Exfiltration
intent-browser-credential-storeskill-card.md:20Accesses a browser credential / cookie storeRisk: Agents can access live browser sessions, cookies, and authenticated Chrome profiles. <br>
-
high Exfiltration
intent-browser-credential-storeskill-card.md:40Accesses a browser credential / cookie store**Other Properties Related to Output:** [Guidance may involve live browser sessions, local files, cookies, Chrome profiles, API keys, cloud browser sessions, and public localhost tunnels.] <br>
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:20Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://browser-use.com/cli/install.sh | bash
-
high Exfiltration
exfil-webhook-urlSKILL.md:246Webhook / callback URL commonly used for exfiltration (verify the destination)browser-use open https://abc.trycloudflare.com
-
high Exfiltration
exfil-webhook-urlSKILL.md:376Webhook / callback URL commonly used for exfiltration (verify the destination)browser-use open https://xyz.trycloudflare.com
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:23Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)& "C:\Program Files\Git\bin\bash.exe" -c 'curl -fsSL https://browser-use.com/cli/install.sh | bash'
quoted -
medium Exfiltration
exfil-webhook-urlSKILL.md:244Webhook / callback URL commonly used for exfiltration (verify the destination) (code comment)browser-use tunnel 3000 # → https://abc.trycloudflare.com
comment -
medium Exfiltration
exfil-webhook-urlSKILL.md:374Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example)# Copy the printed public URL, e.g. https://xyz.trycloudflare.com
demo
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3349 tokens
- 100Running it twice. No mutating operations
- low 16 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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 39 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (33 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.