FB chrome-for-openclaw
Browser automation CLI for AI agents using Google Chrome via CDP. Connects to a running Chrome instance started by chrome_for_openclaw.sh inside an XRDP session. Use when the user needs to interact with websites using their existing login sessions, navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, or automating browser tasks.
As a process B 70/100 · Nearly there — weak spots: result and completion, running it twice
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.
- 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-storereferences/authentication.md:24Accesses a browser credential / cookie storeThe fastest way to authenticate is to reuse cookies from a Chrome session you are already logged into.
-
high Exfiltration
intent-browser-credential-storereferences/authentication.md:41Accesses a browser credential / cookie store> **Security note:** `--remote-debugging-port` exposes full browser control on localhost. Any local process can connect and read cookies, execute JS, etc. Only use on trusted machines and close Chrome
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:31Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -fsSL https://raw.githubusercontent.com/joustonhuang/chrome_for_openclaw/main/chrome_for_openclaw.sh) --install
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:38Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -fsSL https://raw.githubusercontent.com/joustonhuang/chrome_for_openclaw/main/chrome_for_openclaw.sh) --reinstall
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:41Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -fsSL https://raw.githubusercontent.com/joustonhuang/chrome_for_openclaw/main/chrome_for_openclaw.sh) --uninstall
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:52Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -fsSL https://raw.githubusercontent.com/joustonhuang/chrome_for_openclaw/main/chrome_for_openclaw.sh)
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:59Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -fsSL https://raw.githubusercontent.com/joustonhuang/chrome_for_openclaw/main/chrome_for_openclaw.sh)
Medium and low: 1
-
low Exfiltration
net-credential-useSKILL.md:168Credential used in a network call (verify the destination is the intended service) (security demo / example; quoted — discussed, not commanded)echo "$PASSWORD" | agent-browser auth save myapp --url https://app.example.com/login --username user --password-stdin
demoquoted
Files scanned: 10. 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 70/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 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 4024 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 top-level sections: this looks like several domains in one skill
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 365: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (32 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.