Ros Agent MCP Server
ros-agent
PyPI
v0.13.0
Published by publu — 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.
Quickly run and manage ROS 1/2 robots. Built-in MCP for Claude, Cursor, or any AI client, plus vision, sim, and hot-reload behaviors. Merkle proofs make every run tamper-evident and replayable.
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 11
high Dynamic code execution in server code (roborun/web/fleet.js)MTC-SRC-001
In the server's implementation (`roborun/web/fleet.js:692`): 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: t"); try { customFn = new Function("r", "H", body); } catch (e) { customFn = null; stat.textContent = "compile error
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 roborun/web/fleet.js
high Dynamic code execution in server code (roborun/web/py/shim.py)MTC-SRC-001
In the server's implementation (`roborun/web/py/shim.py:59`): 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: t = {} try: exec(compile(source, "player_policy.py", "exec"), ns) except Exception as exc: retur
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 roborun/web/py/shim.py
high Shell/command execution in server code (roborun/routes/launch.py)MTC-SRC-002
In the server's implementation (`roborun/routes/launch.py:64`): 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: ry: completed = subprocess.run(args, cwd=str(ROOT), env=merged, text=True, st
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 roborun/routes/launch.py
high Shell/command execution in server code (roborun/skills/manager.py)MTC-SRC-002
In the server's implementation (`roborun/skills/manager.py:165`): 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: None) -> str: out = subprocess.run(["git", *args], cwd=cwd, capture_output=True, text=True,
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 roborun/skills/manager.py
high Shell/command execution in server code (roborun/web/fleet-sim.js)MTC-SRC-002
In the server's implementation (`roborun/web/fleet-sim.js:39`): 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: ck = 0; } function spawn() { S.robots = []; S.detections = 0; S.detectedKeys = new Set(); S.t0 = performance.no
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 roborun/web/fleet-sim.js
high Shell/command execution in server code (roborun/web/physics.js)MTC-SRC-002
In the server's implementation (`roborun/web/physics.js: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: /* ── robot ── */ spawn(x, z, hdg) { heading = hdg || 0; alt = profile.fly ? 1.0 : standY; robot
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 roborun/web/physics.js
high Shell/command execution in server code (roborun/web/py/shim.py)MTC-SRC-002
In the server's implementation (`roborun/web/py/shim.py:59`): 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: t = {} try: exec(compile(source, "player_policy.py", "exec"), ns) except Exception as exc: retur
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 roborun/web/py/shim.py
medium Dynamic module load from a non-literal (roborun/web/wasm.js)MTC-SRC-005
In the server's implementation (`roborun/web/wasm.js:14`): 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: { loadPyodide } = await import(PYODIDE_URL); const py = await loadPyodide(); status("installing mcap + cryptography
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 roborun/web/wasm.js
low Dynamic code execution in packaging/dev tooling (tests/test_demo_policy.py)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_demo_policy.py:192`): 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 behavior\n", "") exec(compile(code, "demo.py", "exec"), ns) policy = ns["player_policy"] robot = SimRobot
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_demo_policy.py
low Shell/command execution in packaging/dev tooling (tests/test_demo_policy.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_demo_policy.py:192`): 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: rt behavior\n", "") exec(compile(code, "demo.py", "exec"), ns) policy = ns["player_policy"] robot = SimRobot
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_demo_policy.py
low Shell/command execution in packaging/dev tooling (tests/test_skills_manager.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_skills_manager.py:41`): 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: -qm", "init"]): subprocess.run(cmd, cwd=repo, check=True, capture_output=True) return repo def test_valida
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_skills_manager.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 1
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 |
|---|---|---|---|---|
v0.13.0 latest |
A 93/100 | 11 | 1.13.0 | 2026-08-25 |
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 ros-agent --online --registry pypiMore in Gaming & Entertainment
Uncensored AI tools (chat, image, RE/malware analysis, JS deobfuscation, multi-step research) for Claude Desktop, Cursor, Cline, Zed, and any MCP client.
儿童故事 MCP 服务 - 提供故事列表和搜索功能
Grade any bet against thousands of play-by-play game simulations: win probability, odds, edge.
World Cup MCP server for the 2026 men's football tournament — live scores, fixtures, standings, read-only prediction-market signals, and paste-ready match cards. Works with Claude Code, Cursor, Codex, Windsurf, Zed. Not affiliated with FIFA or Anthropic.
MCP server exposing a live Dwarf Fortress fort to an AI agent as curated, semantic tools
MCP Server for Arknights: Endfield (TypeScript / stdio + Streamable HTTP)