Sassymcp MCP Server
sassymcp
PyPI
v1.13.0
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
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 − 26.5 = 74. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −22 | Hardcoded AWS access key id in server code MTC-SRC-008 | exfiltration |
| −2.1 | Package has no source repository MTC-SUP-011 | supply-chain |
| −1.2 | Excessive ALL-CAPS emphasis in metadata MTC-INJ-CAPS | injection |
| −1.2 | Conditional behavior directive MTC-INJ-SEQ-2 | injection |
2. Client adoption risk — 74 − 15 = 59. 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 |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −5 | publisher verification (unlocatable) — no provenance and no public repository to inspect |
| ✓ | inspection depth (source) — how much of the target the scan could see |
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 a deduction.
Findings 42
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: sassy_combo_pr_review → sassy_gh_get_file_contents → sassy_adb_shell. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow sassy_combo_pr_review → sassy_gh_get_file_contents → sassy_adb_shell
high Reads a sensitive credential path or dumps the environment (sassymcp/modules/_security.py)MTC-SRC-006
In the server's implementation (`sassymcp/modules/_security.py:638`): 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 sassymcp/modules/_security.py
high Reads a sensitive credential path or dumps the environment (sassymcp/modules/fileops.py)MTC-SRC-006
In the server's implementation (`sassymcp/modules/fileops.py:212`): 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 sassymcp/modules/fileops.py
high Reads a sensitive credential path or dumps the environment (sassymcp/modules/linux.py)MTC-SRC-006
In the server's implementation (`sassymcp/modules/linux.py:13`): 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 sassymcp/modules/linux.py
high Reads a sensitive credential path or dumps the environment (sassymcp/overlay/mesh.py)MTC-SRC-006
In the server's implementation (`sassymcp/overlay/mesh.py:42`): 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: dict(os.environ)
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 sassymcp/overlay/mesh.py
high Reads a sensitive credential path or dumps the environment (tools/verify_audit_fixes.py)MTC-SRC-006
In the server's implementation (`tools/verify_audit_fixes.py:186`): 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: id_rsa
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 tools/verify_audit_fixes.py
high Hardcoded AWS access key id in server code (tools/verify_audit_fixes.py)MTC-SRC-008
A live-looking AWS access key id is hardcoded in `tools/verify_audit_fixes.py:329`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: AWS access key id: AKIA…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tools/verify_audit_fixes.py
high Tool "sassy_adb_shell" exposes command/code executionMTC-CAP-001
Tool "sassy_adb_shell" appears to run shell commands or evaluate code (keyword "shell"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool sassy_adb_shell
high Tool "sassy_launch_app" exposes command/code executionMTC-CAP-001
Tool "sassy_launch_app" appears to run shell commands or evaluate code (keyword "exec"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool sassy_launch_app
high Tool "sassy_audit_false_positives" exposes command/code executionMTC-CAP-001
Tool "sassy_audit_false_positives" appears to run shell commands or evaluate code (keyword "shell"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool sassy_audit_false_positives
high Tool "sassy_linux_exec" exposes command/code executionMTC-CAP-001
Tool "sassy_linux_exec" appears to run shell commands or evaluate code (keyword "exec"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool sassy_linux_exec
high Dynamic code execution in server code (sassymcp/modules/persona.py)MTC-SRC-001
In the server's implementation (`sassymcp/modules/persona.py:140`): 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: eval(
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 sassymcp/modules/persona.py
high Shell/command execution in server code (sassymcp-vscode/src/cockpitData.ts)MTC-SRC-002
In the server's implementation (`sassymcp-vscode/src/cockpitData.ts:10`): 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: child_process
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 sassymcp-vscode/src/cockpitData.ts
high Shell/command execution in server code (sassymcp-vscode/src/hermes.ts)MTC-SRC-002
In the server's implementation (`sassymcp-vscode/src/hermes.ts:8`): 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: child_process
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 sassymcp-vscode/src/hermes.ts
high Shell/command execution in server code (sassymcp-vscode/src/installer.ts)MTC-SRC-002
In the server's implementation (`sassymcp-vscode/src/installer.ts:12`): 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: child_process
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 sassymcp-vscode/src/installer.ts
high Shell/command execution in server code (sassymcp-vscode/src/setupWizard.ts)MTC-SRC-002
In the server's implementation (`sassymcp-vscode/src/setupWizard.ts:14`): 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: child_process
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 sassymcp-vscode/src/setupWizard.ts
high Shell/command execution in server code (sassymcp/_jobctl.py)MTC-SRC-002
In the server's implementation (`sassymcp/_jobctl.py:49`): 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 sassymcp/_jobctl.py
high Shell/command execution in server code (sassymcp/_phone_status.py)MTC-SRC-002
In the server's implementation (`sassymcp/_phone_status.py:31`): 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 sassymcp/_phone_status.py
high Shell/command execution in server code (sassymcp/_platform.py)MTC-SRC-002
In the server's implementation (`sassymcp/_platform.py:30`): 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 sassymcp/_platform.py
high Shell/command execution in server code (sassymcp/auth.py)MTC-SRC-002
In the server's implementation (`sassymcp/auth.py:102`): 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 sassymcp/auth.py
high Shell/command execution in server code (sassymcp/desktop/bridge.py)MTC-SRC-002
In the server's implementation (`sassymcp/desktop/bridge.py:112`): 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 sassymcp/desktop/bridge.py
high Shell/command execution in server code (sassymcp/modules/app_launcher.py)MTC-SRC-002
In the server's implementation (`sassymcp/modules/app_launcher.py:479`): 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 sassymcp/modules/app_launcher.py
medium Tool "sassy_write_file" can modify the filesystemMTC-CAP-002
Tool "sassy_write_file" can write, overwrite or delete files (keyword "write_file"). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool sassy_write_file
medium Tool "sassy_move" can modify the filesystemMTC-CAP-002
Tool "sassy_move" can write, overwrite or delete files (keyword "overwrite"). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool sassy_move
medium Tool "sassy_copy" can modify the filesystemMTC-CAP-002
Tool "sassy_copy" can write, overwrite or delete files (keyword "overwrite"). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool sassy_copy
medium Tool "sassy_gh_create_file" can modify the filesystemMTC-CAP-002
Tool "sassy_gh_create_file" can write, overwrite or delete files (keyword "create_file"). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool sassy_gh_create_file
medium Tool "sassy_gh_delete_file" can modify the filesystemMTC-CAP-002
Tool "sassy_gh_delete_file" can write, overwrite or delete files (keyword "delete_file"). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool sassy_gh_delete_file
medium Dynamic module load from a non-literal (sassymcp/modules/setup_wizard.py)MTC-SRC-005
In the server's implementation (`sassymcp/modules/setup_wizard.py:836`): 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: __import__(
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 sassymcp/modules/setup_wizard.py
medium Dynamic module load from a non-literal (sassymcp/server.py)MTC-SRC-005
In the server's implementation (`sassymcp/server.py:285`): 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: __import__(
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 sassymcp/server.py
medium Dynamic module load from a non-literal (tools/verify_audit_fixes.py)MTC-SRC-005
In the server's implementation (`tools/verify_audit_fixes.py:467`): 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: __import__(
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 tools/verify_audit_fixes.py
low Mutating tool "sassy_adb_shell" declares no destructiveHintMTC-CAP-005
Tool "sassy_adb_shell" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_adb_shell
low Mutating tool "sassy_launch_app" declares no destructiveHintMTC-CAP-005
Tool "sassy_launch_app" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_launch_app
low Mutating tool "sassy_audit_false_positives" declares no destructiveHintMTC-CAP-005
Tool "sassy_audit_false_positives" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_audit_false_positives
low Mutating tool "sassy_write_file" declares no destructiveHintMTC-CAP-005
Tool "sassy_write_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_write_file
low Mutating tool "sassy_move" declares no destructiveHintMTC-CAP-005
Tool "sassy_move" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_move
low Mutating tool "sassy_copy" declares no destructiveHintMTC-CAP-005
Tool "sassy_copy" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_copy
low Mutating tool "sassy_gh_create_file" declares no destructiveHintMTC-CAP-005
Tool "sassy_gh_create_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_gh_create_file
low Mutating tool "sassy_gh_delete_file" declares no destructiveHintMTC-CAP-005
Tool "sassy_gh_delete_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_gh_delete_file
low Mutating tool "sassy_linux_exec" declares no destructiveHintMTC-CAP-005
Tool "sassy_linux_exec" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool sassy_linux_exec
low Excessive ALL-CAPS emphasis in metadataMTC-INJ-CAPS
A run of shouted words is a common way to give injected instructions false authority.
Evidence: Send a key event. Common keycodes: KEYCODE_HOME, KEYCODE_BACK,
KEYCODE_ENTER, KEYCODE_VOLUME_UP, KEYCODE_VOLUME_
Location: tool sassy_phone_key · description
low Conditional behavior directiveMTC-INJ-SEQ-2
Conditional behavior directive detected in the description of tool "sassy_phone_pause". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: When use
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool sassy_phone_pause · description
low Package has no source repositoryMTC-SUP-011
"sassymcp" 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 sassymcp
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (200 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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 |
|---|---|---|---|---|
v1.13.0 latest |
F 59/100 | 42 | 1.7.0 | 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 sassymcp --online --registry pypiMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Agent MCP server.
Security scan results for the Agent Recorder MCP server.