Agentpool Cli — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "agentpool-cli",
"source": {
"kind": "package",
"origin": "agentpool-cli"
},
"server": {
"name": "agentpool-cli"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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-1.9"
},
"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 (29 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 \"spawn_worker\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_worker\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "spawn_worker"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agentpool/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agentpool/cli.py:1611`): 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/agentpool/cli.py"
},
"evidence": "e) @app.command() def spawn( provider: Annotated[str, typer.Option(\"--provider\", help=\"Explicit provider id.\")],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agentpool/cli.py",
"line": 1611,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agentpool/runtimes/base.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agentpool/runtimes/base.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.",
"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/agentpool/runtimes/base.py"
},
"evidence": "d: RuntimeKind def spawn( self, command: list[str], cwd: Path, env: dict[str, str], session_name: str )",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agentpool/runtimes/base.py",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agentpool/runtimes/terminal_control.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agentpool/runtimes/terminal_control.py:55`): 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/agentpool/runtimes/terminal_control.py"
},
"evidence": "se self.binary def spawn( self, command: list[str], cwd: Path, env: dict[str, str]",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agentpool/runtimes/terminal_control.py",
"line": 55,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agentpool/runtimes/tmux.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agentpool/runtimes/tmux.py:23`): 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/agentpool/runtimes/tmux.py"
},
"evidence": "lf.tmux_binary def spawn( self, command: list[str], cwd: Path, env: dict[str, str] | None, session_name: st",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agentpool/runtimes/tmux.py",
"line": 23,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agentpool/utils.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agentpool/utils.py:75`): 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/agentpool/utils.py"
},
"evidence": "cess.DEVNULL proc = subprocess.Popen( args, cwd=str(cwd) if cwd else None, stdin=stdin,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agentpool/utils.py",
"line": 75,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_worker\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_worker\" 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": "spawn_worker"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/integration/test_fake_tmux_flow.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_fake_tmux_flow.py:170`): 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/integration/test_fake_tmux_flow.py"
},
"evidence": "subprocess return subprocess.run(args, cwd=str(cwd), text=True, capture_output=True, check=False).returncode",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/integration/test_fake_tmux_flow.py",
"line": 170,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/unit/test_mcp_surface.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_mcp_surface.py:326`): 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/unit/test_mcp_surface.py"
},
"evidence": "PollingRuntime: def spawn( self, command: list[str], cwd: Path, env: dict[str, str],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/unit/test_mcp_surface.py",
"line": 326,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/unit/test_mcp_tools.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_mcp_tools.py:29`): 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/unit/test_mcp_tools.py"
},
"evidence": "lf.screen = \"\" def spawn(self, command: list[str], cwd: Path, env: dict[str, str], session_name: str) -> TmuxSessio",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/unit/test_mcp_tools.py",
"line": 29,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/unit/test_models_config_store.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_models_config_store.py:52`): 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/unit/test_models_config_store.py"
},
"evidence": "t | None] = [] def spawn( self, command: list[str], cwd: Path, env: dict[str, str],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/unit/test_models_config_store.py",
"line": 52,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/unit/test_redaction.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_redaction.py:52`): 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/unit/test_redaction.py"
},
"evidence": "import subprocess subprocess.run([\"git\", \"init\"], cwd=repo, check=True, capture_output=True) subprocess.run([\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/unit/test_redaction.py",
"line": 52,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"agentpool-cli\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "agentpool-cli"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"agentpool-cli\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "agentpool-cli"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_inventory",
"tags": [],
"reasons": {}
},
{
"tool": "get_usage_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "get_cached_usage_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "get_usage_summary",
"tags": [],
"reasons": {}
},
{
"tool": "get_capacity_summary",
"tags": [],
"reasons": {}
},
{
"tool": "get_stats",
"tags": [],
"reasons": {}
},
{
"tool": "get_stats_card",
"tags": [],
"reasons": {}
},
{
"tool": "get_provider_models",
"tags": [],
"reasons": {}
},
{
"tool": "get_delegation_preferences",
"tags": [],
"reasons": {}
},
{
"tool": "validate_model_catalog",
"tags": [],
"reasons": {}
},
{
"tool": "filter_candidates",
"tags": [],
"reasons": {}
},
{
"tool": "spawn_worker",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "observe_worker",
"tags": [],
"reasons": {}
},
{
"tool": "poll_worker",
"tags": [],
"reasons": {}
},
{
"tool": "send_worker_message",
"tags": [],
"reasons": {}
},
{
"tool": "send_worker_keys",
"tags": [],
"reasons": {}
},
{
"tool": "interrupt_worker",
"tags": [],
"reasons": {}
},
{
"tool": "attach_info",
"tags": [],
"reasons": {}
},
{
"tool": "collect_worker_artifacts",
"tags": [],
"reasons": {}
},
{
"tool": "get_artifact_manifest",
"tags": [],
"reasons": {}
},
{
"tool": "read_worker_transcript",
"tags": [],
"reasons": {}
},
{
"tool": "acquire_file_lease",
"tags": [],
"reasons": {}
},
{
"tool": "list_file_leases",
"tags": [],
"reasons": {}
},
{
"tool": "release_file_lease",
"tags": [],
"reasons": {}
},
{
"tool": "list_worktrees",
"tags": [],
"reasons": {}
},
{
"tool": "cleanup_worktree",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "get_session",
"tags": [],
"reasons": {}
},
{
"tool": "terminate_worker",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "930d1f2444f579aa538feeb16dc806b8fbd9009e07fb4feb602d31e37c01d311",
"stats": {
"tools": 29,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 6,
"info": 2
}
}
}