Aworld MCP Server
aworld
PyPI
v0.3.2
Published by inclusionai — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.
Every server starts at 100. These are the exact deductions the deterministic engine applied — each one reproducible, none of it an opinion or an LLM's guess:
| Points | What was found | Category |
|---|---|---|
| −11 | Unsafe deserialization ×3 MTC-SRC-007 | permissions |
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 the deduction.
Findings 8
high Shell/command execution in server code (aworld/agents/llm_agent.py)MTC-SRC-002
In the server's implementation (`aworld/agents/llm_agent.py:276`): 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: spawn(
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 aworld/agents/llm_agent.py
high Shell/command execution in server code (aworld/cmd/utils/agent_loader.py)MTC-SRC-002
In the server's implementation (`aworld/cmd/utils/agent_loader.py:45`): 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: subprocess.Popen(
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 aworld/cmd/utils/agent_loader.py
high Shell/command execution in server code (aworld/core/agent/subagent_manager.py)MTC-SRC-002
In the server's implementation (`aworld/core/agent/subagent_manager.py:287`): 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: spawn(
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 aworld/core/agent/subagent_manager.py
high Shell/command execution in server code (aworld/experimental/ptc/ptc_tool.py)MTC-SRC-002
In the server's implementation (`aworld/experimental/ptc/ptc_tool.py:233`): 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: exec(
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 aworld/experimental/ptc/ptc_tool.py
high Shell/command execution in server code (aworld/output/code_artifact.py)MTC-SRC-002
In the server's implementation (`aworld/output/code_artifact.py:183`): 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: subprocess.run(
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 aworld/output/code_artifact.py
medium Unsafe deserialization (aworld/cmd/utils/trace_summarize.py)MTC-SRC-007
In the server's implementation (`aworld/cmd/utils/trace_summarize.py:27`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: pickle.load(
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 aworld/cmd/utils/trace_summarize.py
medium Unsafe deserialization (aworld/core/storage/multi_process_store.py)MTC-SRC-007
In the server's implementation (`aworld/core/storage/multi_process_store.py:71`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: pickle.loads(
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 aworld/core/storage/multi_process_store.py
medium Unsafe deserialization (aworld/events/redis_backend.py)MTC-SRC-007
In the server's implementation (`aworld/events/redis_backend.py:52`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: pickle.loads(
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 aworld/events/redis_backend.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
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 |
|---|---|---|---|---|
v0.3.2 latest |
B 89/100 | 8 | 1.5.0 | 2026-07-23 |
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 aworld --online --registry pypiMore in Data Science & ML
Security scan results for the 2sio MCP server.
Security scan results for the Ab Ibge MCP server.
Security scan results for the Abgeordnetenwatch MCP server.
Security scan results for the Acta MCP server.
Security scan results for the Adapter MCP server.
Security scan results for the Addon MCP server.