Vibatchium MCP Server
vibatchium
PyPI
v0.19.2
Published by trueoriginlabs — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Patchwright stealth + Vibium-style LLM-friendly CLI for agentic browser automation.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 12
high Dynamic code execution in server code (vibatchium/oracle.py)MTC-SRC-001
In the server's implementation (`vibatchium/oracle.py:719`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt so an isolated-world eval (Patchright) or any automated harness can read the trials without the download button
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vibatchium/oracle.py
medium Dynamic module load from a non-literal (vibatchium/cli.py)MTC-SRC-005
In the server's implementation (`vibatchium/cli.py:330`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: __import__(modname) lane(name, True, f"available — {what}") except Exception
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vibatchium/cli.py
low Shell/command execution in packaging/dev tooling (tests/test_daemon_log_persist.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_daemon_log_persist.py:32`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: r a in attrs) out = subprocess.run( [sys.executable, "-c", code], capture_output=True, text=True, en
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_daemon_log_persist.py
low Shell/command execution in packaging/dev tooling (tests/test_daemon_singleton.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_daemon_singleton.py:51`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ld code).""" proc = subprocess.run( [sys.executable, "-m", "vibatchium.daemon.server"], env=os.envir
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_daemon_singleton.py
low Shell/command execution in packaging/dev tooling (tests/test_integration_daemon.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_integration_daemon.py:68`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: on: self.proc = subprocess.Popen( [sys.executable, "-m", "vibatchium.daemon.server"], en
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_integration_daemon.py
low Shell/command execution in packaging/dev tooling (tests/test_wave6_warmup.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave6_warmup.py:230`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: out = subprocess.check_output( ["ps", "-e", "-o", "args="], text=True, errors="ignore", ti
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave6_warmup.py
low Shell/command execution in packaging/dev tooling (tests/test_wave7_audit_fixes.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave7_audit_fixes.py:134`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rks_via_help(): r = subprocess.run([_vibatchium_bin(), "set_log_verbs", "--help"], capture_out
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave7_audit_fixes.py
low Shell/command execution in packaging/dev tooling (tests/test_wave7_codex_friction.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave7_codex_friction.py:75`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: l_form_works(): r = subprocess.run([_vibatchium_bin(), "verify-url", "https://example.com"], c
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave7_codex_friction.py
low Shell/command execution in packaging/dev tooling (tests/test_wave7_default_headless.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave7_default_headless.py:23`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: the help.""" out = subprocess.run( [sys.executable, "-m", "vibatchium.cli", "daemon", "start", "--help"],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave7_default_headless.py
low Shell/command execution in packaging/dev tooling (tests/test_wave7_onboarding.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave7_onboarding.py:20`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ts_options(): out = subprocess.run( [sys.executable, "-m", "vibatchium.cli", "logs", "--help"], capt
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave7_onboarding.py
low Shell/command execution in packaging/dev tooling (tests/test_wave7_recycle_and_walled.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave7_recycle_and_walled.py:152`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: leep(0.3) out = subprocess.run( [sys.executable, "-m", "vibatchium.cli", "logs", "--sin
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave7_recycle_and_walled.py
low Shell/command execution in packaging/dev tooling (tests/test_wave7_research.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_wave7_research.py:125`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ints help.""" out = subprocess.run( [sys.executable, "-m", "vibatchium.cli", "research", "--help"],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_wave7_research.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 4
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.19.2 latest |
A 93/100 | 12 | 1.13.0 | 2026-08-27 |
v0.18.14 |
A 93/100 | 12 | 1.13.0 | 2026-08-25 |
v0.18.12 |
A 93/100 | 12 | 1.12.1 | 2026-08-04 |
v0.18.6 |
A 93/100 | 12 | 1.12.1 | 2026-07-27 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan vibatchium --online --registry pypiMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai