Skills/PyPI/gemini-web-mcp-cli

gemini-web-mcp-cli@0.12.0

CAUTION· not started

Publisher claims: "MCP server and CLI for the Gemini web interface" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher jacob-bd · publishing for 294 daysInstalls 1,556Last detonated 7 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
no vendor host named in the codeAlso google.com, apple.com, astral.sh, gstatic.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx gemini-web-mcp-cli

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.9.7

vet-skills diff gemini-web-mcp-cli 0.9.7 0.12.0

This version reaches for something 0.9.7 did not: 1 new host (astral.sh). Compared from the two recorded runs, not from source.

New hosts
astral.sh

0.9.7 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Credential pass-through configuration; Sends the whole process environment out. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.4sprocessdependency install exit 1 ·
0.4sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

CRITICAL
Pipe-to-shell patterndesktop-extension/run_server.py:68 · Pipe-to-shell pattern — downloads and immediately executes remote code" curl -LsSf https://astral.sh/uv/install.sh | sh\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:915 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:898 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:222 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/keepalive.py:340 · Python subprocess execution detectedself._process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationsrc/gemini_web_mcp_cli/core/cdp.py:1298 · Credential pass-through configuration — agent relays sensitive credentialspassFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:852 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:835 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:501 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/cdp.py:241 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:877 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/cdp.py:996 · Python subprocess execution detectedprocess = subprocess.Popen(args, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/hack.py:121 · Python subprocess execution detectedresult = subprocess.run(cmd, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/daemon_idle.py:108 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Sends the whole process environment outsrc/gemini_web_mcp_cli/core/cdp.py:477 · Sends the whole process environment out"""Read browser preference from GEMCLI_BROWSER env > config.json > 'auto'.Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/cdp.py:1431 · Python subprocess execution detectedself._process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompting user to enter sensitive credentialssrc/gemini_web_mcp_cli/core/keepalive.py:427 · Prompting user to enter sensitive credentials — social engineeringif "challenge/pwd" in url or "enter your password" in t:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/cli.py:2775 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/cdp.py:1178 · Python subprocess execution detectedchrome_process = subprocess.Popen(args, **popen_kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/cli.py:1340 · Python subprocess execution detected (subprocess.Popen via alias)sp.Popen(["start", str(saved)], shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/auth.py:372 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/cli.py:1336 · Python subprocess execution detected (subprocess.Popen via alias)sp.Popen(["open", str(saved)])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/hack.py:72 · Python subprocess execution detectedserver_process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/daemon_idle.py:147 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/daemon_idle.py:218 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detecteddesktop-extension/run_server.py:76 · Python subprocess execution detectedos.execvp(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:170 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/token_factory.py:1712 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/chrome_manager.py:268 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/keepalive.py:223 · Python subprocess execution detectedout = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/core/token_factory.py:845 · Python subprocess execution detectedself._process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/cli.py:1338 · Python subprocess execution detected (subprocess.Popen via alias)sp.Popen(["xdg-open", str(saved)])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/core/chrome_manager.py:229 · Process kill command — agent can terminate processes# If ps fails, trust os.kill resultFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingsrc/gemini_web_mcp_cli/services/image.py:30 · Dynamic module loadingmod = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/cli.py:2221 · Process kill command — agent can terminate processes"""Scan for and kill zombie Chrome processes.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:728 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_locks.py:80 · Python subprocess execution detectedproc = subprocess.Popen([sys.executable, "-c", code], stdout=subprocess.PIPE, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:414 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_token_factory.py:712 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/gemini_web_mcp_cli/skill.py:434 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Install/update AGENTS.md format (append with markers)."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:220 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsrc/gemini_web_mcp_cli/core/profiles.py:350 · File type combined with upload action — agent may exfiltrate local data files# (it doesn't put chrome_profile_path in auth.json -- the path is computed).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:423 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:271 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_chrome_manager.py:197 · Process kill command — agent can terminate processes# os.kill should not raise for our own processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/core/chrome_manager.py:630 · Process kill command — agent can terminate processes# Force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_auth.py:401 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:248 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/core/cdp.py:138 · Process kill command — agent can terminate processes# False as "zombie" and kill it.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shelldesktop-extension/run_server.py:68 · Remote installer piped to shell" curl -LsSf https://astral.sh/uv/install.sh | sh\n"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:382 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Prompting user to enter sensitive credentialstests/test_keepalive.py:72 · Prompting user to enter sensitive credentials — social engineering("https://accounts.google.com/x", "Enter your password", "password"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python exec or eval of computed codetests/test_token_factory.py:688 · Python exec or eval of computed codeeval(script).then(result => {Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandtests/test_auth.py:395 · Process kill command — agent can terminate processes"""Killing one profile's Chrome must not kill a sibling (profile-a vs profile-b)."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_locks.py:172 · Process kill command — agent can terminate processeskill = terminateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/core/token_factory.py:701 · Process kill command — agent can terminate processesHolds the profile lock so two processes never launch, kill or driveFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/core/chrome_manager.py:361 · Process kill command — agent can terminate processes"""Scan the port map and kill any zombie Chrome instances.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/gemini_web_mcp_cli/setup.py:713 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/gemini_web_mcp_cli/core/cdp.py:191 · Process kill command — agent can terminate processes# Still alive — force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingsrc/gemini_web_mcp_cli/services/image.py:31 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(mod)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈19,123 tok
3 files · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for gemini-web-mcp-cli@0.12.0 as of 6 h ago. This is the package itself, not its dependencies.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Unclaimed publisher≈ +8 on the totalClaim jacob-bd: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Sends the whole process environment out≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jacob-bdPropose a patch to the maintainer