Skills/PyPI/mcp-browser

mcp-browser@2.2.63

CAUTION· not started

Publisher claims: "Browser control and console log capture for AI coding assistants via MCP" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher browserpymcp · publishing for 417 daysInstalls 118Last detonated 8d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-browser` runs it now and prints the full answer.

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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 77/100 (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; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 1:
0.1sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.2sprocessdependency install exit 1
0.2sprocessexec /usr/bin/date
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/mcp-browser
0.2sclaimedno tools/list reply (exit 0)
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexec /usr/bin/faketime
0.3sprocessexec /usr/bin/dirname
0.3sprocessexited 1:
0.3sprocessexec /usr/bin/faketime
0.3sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

HIGH
Access to sensitive file pathsscripts/dev-extension.sh:149 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho -e "${YELLOW}Set CHROME_EXECUTABLE_PATH in .env.development or install Chrome${NC}"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/bump_version.py:265 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/dev-full.sh:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescp "$PROJECT_ROOT/.env.development" "$ENV_FILE" 2>/dev/null || trueFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/dev-full.sh:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILE="$PROJECT_ROOT/.env.development"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/dev-extension.sh:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILE="${PROJECT_ROOT}/.env.development"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/dev-server.sh:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesENV_FILE="${PROJECT_ROOT}/.env.development"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/dev-extension.sh:140 · Process kill command — agent can terminate processesif kill -0 $CHROME_PID 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/release.py:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprint(f"{Colors.RED}ERROR: .env.local not found{Colors.NC}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/release.py:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprint(f"{Colors.YELLOW}Create .env.local with required tokens:{Colors.NC}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/release.py:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file = PROJECT_ROOT / '.env.local'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/release.py:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesSystemExit: If .env.local not found or invalidFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/bump_version.py:248 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/dev_runner.py:103 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file = Path(".env.development")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/dev-full.sh:47 · Process kill command — agent can terminate processesif kill -0 "$CHROME_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/build_extension.py:252 · 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 detectedscripts/bump_version.py:196 · 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 detectedscripts/bump_version.py:240 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/bump_version.py:208 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandscripts/install.sh:59 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get update && sudo apt-get install -y pipxFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/release.py:48 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Load environment variables from .env.local file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandscripts/dev-full.sh:59 · Process kill command — agent can terminate processeskill "$SERVER_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/cli/commands/doctor.py:517 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/_version.py:72 · 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/cli/utils/extension.py:130 · 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/cli/utils/daemon.py:226 · Python subprocess execution detectedcwd_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/cli/utils/daemon.py:364 · Process kill command — agent can terminate processes# Then scan all ports and kill ALL mcp-browser processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/_version.py:38 · 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 detectedscripts/release.py:198 · Python subprocess execution detectedcov_available = 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/cli/commands/doctor.py:575 · 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 commandscripts/dev-full.sh:76 · Process kill command — agent can terminate processeskill -0 "$pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/cli/commands/doctor.py:471 · Process kill command — agent can terminate processes"fix": "Restart server: kill existing process and run 'mcp-browser start'",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:154 · 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/cli/utils/extension.py:162 · 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/cli/utils/daemon.py:213 · Python subprocess execution detectedproc_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:201 · Python subprocess execution detected).returncode == 0 and subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/dev-full.sh:49 · Process kill command — agent can terminate processeskill "$CHROME_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/dev-server.sh:51 · Process kill command — agent can terminate processeskill "$PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/dev-server.sh:41 · Process kill command — agent can terminate processeskill "$OLD_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:114 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/dev-full.sh:57 · Process kill command — agent can terminate processesif kill -0 "$SERVER_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/cli/utils/daemon.py:408 · Process kill command — agent can terminate processes# Only kill if process cwd matches THIS projectFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/_version.py:55 · 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/cli/utils/daemon.py:312 · Python subprocess execution detectedproc_result = 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/cli/utils/daemon.py:204 · 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 commandscripts/dev-server.sh:38 · Process kill command — agent can terminate processesif kill -0 "$OLD_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/cli/utils/validation.py:56 · 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/cli/utils/daemon.py:299 · 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 detectedscripts/release.py:90 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.md:22 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file- `chrome://extensions` → enable Developer mode → “Load unpacked” → select `~/mcp-browser-extensions/chrome/`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:22 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file- `chrome://extensions` → enable Developer mode → “Load unpacked” → select `~/mcp-browser-extensions/chrome/`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsrc/extension/Readability.js:1524 · File type combined with upload action — agent may exfiltrate local data filesthis.log("Article content post-prep: " + articleContent.innerHTML);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Authorization escalation languagesrc/extensions/README.md:149 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file2. Enable "Developer mode"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionsrc/extensions/README.md:149 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file2. Enable "Developer mode"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Context shift attemptREADME.md:22 · Context shift attempt — trying to change operational mode · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file- `chrome://extensions` → enable Developer mode → “Load unpacked” → select `~/mcp-browser-extensions/chrome/`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈54 tok
1 file · 81 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 mcp-browser@2.2.63 as of 6 h ago. This is the package itself, not its dependencies.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim browserpymcp: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim browserpymcpPropose a patch to the maintainer