Tmux Agents — the complete, unedited output of the deterministic mcptrustchecker engine v1.14.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.14.0",
"methodologyVersion": "mcptrustchecker-1.14"
},
"target": {
"id": "tmux-agents",
"source": {
"kind": "package",
"origin": "tmux-agents"
},
"server": {
"name": "tmux-agents"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.14"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (26 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>\"."
]
},
"findings": [
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"pane_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"pane_exec\" appears to run shell commands or evaluate code (keyword \"exec\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "pane_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tmux_agents/hook.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tmux_agents/hook.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.",
"remediation": "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": {
"kind": "server",
"name": "src/tmux_agents/hook.py"
},
"evidence": "try: done = subprocess.run( [ \"tmux\", \"list-panes\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tmux_agents/hook.py",
"line": 125,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tmux_agents/notify.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tmux_agents/notify.py:80`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/tmux_agents/notify.py"
},
"evidence": "try: done = subprocess.run( [\"gh\", *args], capture_output=True, text=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tmux_agents/notify.py",
"line": 80,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tmux_agents/tmux.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tmux_agents/tmux.py:130`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/tmux_agents/tmux.py"
},
"evidence": "try: proc = subprocess.run( argv, capture_output=True, text=True, timeout=timeout, check=Fal",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tmux_agents/tmux.py",
"line": 130,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"pane_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"pane_exec\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "pane_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/conftest.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/conftest.py:25`): 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.",
"remediation": "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": {
"kind": "server",
"name": "tests/conftest.py"
},
"evidence": "same so we catch it subprocess.run([\"tmux\", \"-L\", socket, \"start-server\"], capture_output=True) subprocess.run([",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/conftest.py",
"line": 25,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_panes_e2e.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_panes_e2e.py:303`): 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.",
"remediation": "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": {
"kind": "server",
"name": "tests/test_panes_e2e.py"
},
"evidence": "ty.openpty() proc = subprocess.Popen(shlex.split(command), stdin=slave, stdout=slave, stderr=slave) try:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_panes_e2e.py",
"line": 303,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "tmux_status",
"tags": [],
"reasons": {}
},
{
"tool": "panes_list",
"tags": [],
"reasons": {}
},
{
"tool": "pane_read",
"tags": [],
"reasons": {}
},
{
"tool": "pane_send",
"tags": [],
"reasons": {}
},
{
"tool": "pane_key",
"tags": [],
"reasons": {}
},
{
"tool": "pane_wait",
"tags": [],
"reasons": {}
},
{
"tool": "events_read",
"tags": [],
"reasons": {}
},
{
"tool": "agents_launch",
"tags": [],
"reasons": {}
},
{
"tool": "pane_add",
"tags": [],
"reasons": {}
},
{
"tool": "pane_resize",
"tags": [],
"reasons": {}
},
{
"tool": "layout_set",
"tags": [],
"reasons": {}
},
{
"tool": "pane_zoom",
"tags": [],
"reasons": {}
},
{
"tool": "pane_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "pane_wait_any",
"tags": [],
"reasons": {}
},
{
"tool": "pane_wait_all",
"tags": [],
"reasons": {}
},
{
"tool": "pane_send_many",
"tags": [],
"reasons": {}
},
{
"tool": "pane_clear",
"tags": [],
"reasons": {}
},
{
"tool": "pane_swap",
"tags": [],
"reasons": {}
},
{
"tool": "pane_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "window_list",
"tags": [],
"reasons": {}
},
{
"tool": "window_new",
"tags": [],
"reasons": {}
},
{
"tool": "window_kill",
"tags": [],
"reasons": {}
},
{
"tool": "window_rename",
"tags": [],
"reasons": {}
},
{
"tool": "session_attach_cmd",
"tags": [],
"reasons": {}
},
{
"tool": "session_kill",
"tags": [],
"reasons": {}
},
{
"tool": "pane_kill",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "46ff9809784829913c0d62d0d16930c77d8aec7f065f61ee03fc67b644520010",
"stats": {
"tools": 26,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 3,
"info": 0
}
}
}