Portal — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "portal-mcp-server",
"source": {
"kind": "package",
"origin": "portal-mcp-server"
},
"server": {
"name": "portal-mcp-server"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 1.2,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-CMD-1",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (14 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-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (portal_mcp_server/connection_manager.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`portal_mcp_server/connection_manager.py:1090`): 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.",
"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": "portal_mcp_server/connection_manager.py"
},
"evidence": "for k in [\"~/.ssh/id_ed25519\", \"~/.ssh/id_rsa\", \"~/.ssh/id_ecdsa\"]: kp = Path(k).expanduser()",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "portal_mcp_server/connection_manager.py",
"line": 1090,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"remote_shell\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"remote_shell\" appears to run shell commands or evaluate code (keyword \"shell\" 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": "remote_shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"remote_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"remote_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": "remote_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"local_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"local_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": "local_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (portal_mcp_server/connection_manager.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`portal_mcp_server/connection_manager.py:104`): 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": "portal_mcp_server/connection_manager.py"
},
"evidence": "Process: return subprocess.run( cmd, shell=True, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "portal_mcp_server/connection_manager.py",
"line": 104,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (portal_mcp_server/credential_agent.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`portal_mcp_server/credential_agent.py:586`): 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": "portal_mcp_server/credential_agent.py"
},
"evidence": "if enable_now: subprocess.run([\"systemctl\", \"--user\", \"daemon-reload\"], check=True) subprocess.run([\"sy",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "portal_mcp_server/credential_agent.py",
"line": 586,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment in packaging/dev tooling (tests/live_smoke.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/live_smoke.py:36`): 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.",
"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/live_smoke.py"
},
"evidence": "path.expanduser(\"~/.ssh/id_ed25519\")) def sect(title): print(f\"\\n{'═' * 70}\\n {title}\\n{'═' * 70}\") async def m",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/live_smoke.py",
"line": 36,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment in packaging/dev tooling (tests/test_live_ssh.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_live_ssh.py:30`): 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.",
"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_live_ssh.py"
},
"evidence": "path.expanduser(\"~/.ssh/id_ed25519\")) # ── Bootstrap: register the test host ───────────────────────────────────── from",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/test_live_ssh.py",
"line": 30,
"nonRuntime": true
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"remote_shell\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"remote_shell\" 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": "remote_shell"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"remote_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"remote_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": "remote_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"local_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"local_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": "local_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-INJ-CMD-1",
"title": "Shell command embedded in tool metadata",
"category": "injection",
"severity": "low",
"confidence": "heuristic",
"description": "Shell command embedded in tool metadata detected in the description of tool \"policy_check\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "tool",
"name": "policy_check",
"field": "description"
},
"evidence": "rm -rf",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "command-in-prose"
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_credential_agent_namedpipe.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_credential_agent_namedpipe.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.",
"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_credential_agent_namedpipe.py"
},
"evidence": "scheduled_task_name subprocess.run([\"schtasks\", \"/Delete\", \"/TN\", default_scheduled_task_name(),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_credential_agent_namedpipe.py",
"line": 118,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_local_sudo.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_local_sudo.py:175`): 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_local_sudo.py"
},
"evidence": "ues([value]) proc = subprocess.run([\"bash\", \"-c\", body], input=payload.encode(), capture_o",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_local_sudo.py",
"line": 175,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "hosts",
"tags": [],
"reasons": {}
},
{
"tool": "remote_transfer",
"tags": [],
"reasons": {}
},
{
"tool": "remote_tunnel",
"tags": [],
"reasons": {}
},
{
"tool": "policy_check",
"tags": [],
"reasons": {}
},
{
"tool": "inspect",
"tags": [],
"reasons": {}
},
{
"tool": "remote_read",
"tags": [],
"reasons": {}
},
{
"tool": "remote_patch",
"tags": [],
"reasons": {}
},
{
"tool": "remote_grep",
"tags": [],
"reasons": {}
},
{
"tool": "remote_glob",
"tags": [],
"reasons": {}
},
{
"tool": "remote_shell",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\" in tool name"
]
}
},
{
"tool": "remote_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "local_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "remote_close",
"tags": [],
"reasons": {}
},
{
"tool": "remote_job",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "576d1f36e37e3d1364b7d2998246e440bbef95d818a94ef6c355e326b5948dc8",
"stats": {
"tools": 14,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 8,
"info": 0
}
}
}