seleniumbase-mcp@1.7.1
CAUTION· install onlyPublisher claims: "MCP servers exposing SeleniumBase as tools for MCP clients." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- seleniumbase.io (its own)
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. The code names no credential variable and talks to seleniumbase.io, its own; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 1.6.1
vet-skills diff seleniumbase-mcp 1.6.1 1.7.1In the sandbox, this version reached for nothing 1.6.1 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; OS command execution function call detected; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 3 scenarios · 0 deviationsStatic findings
# (e.g., "../../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.os.system("python -m pip install --upgrade 'pkginfo'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("rm -f dist/*.egg; rm -f dist/*.tar.gz; rm -f dist/*.whl")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install --upgrade 'twine'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.flake8_status = os.system(Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install 'flake8==7.5.0'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("rm -rf build/bdist.*; rm -rf build/lib")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install --upgrade 'more-itertools'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install --upgrade 'readme-renderer'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m twine upload dist/*") # Requires ~/.pypirc KeysFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m build") # Create new tar/wheelFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install --upgrade 'jaraco.classes'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install --upgrade 'build'")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system("python -m pip install --upgrade keyring requests-toolbelt")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for seleniumbase-mcp@1.7.1 as of 7 min ago. This is the package itself, not its dependencies.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim seleniumbase: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.