Imsg — the complete, unedited output of the deterministic mcptrustchecker engine v1.7.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.7.0",
"methodologyVersion": "mcptrustchecker-1.7"
},
"target": {
"id": "imsg-mcp",
"source": {
"kind": "package",
"origin": "imsg-mcp"
},
"server": {
"name": "imsg-mcp"
}
},
"grade": "B",
"score": {
"score": 86,
"threatScore": 96,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 3.6,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-TARGET-2",
"category": "injection",
"severity": "medium",
"confidence": "heuristic",
"rawWeight": 9,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 3.6
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"kind": "client",
"term": "verification-discount",
"level": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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-1.7"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"external-sink",
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (23 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-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: get_attachment → get_logs → check_imessage_availability. 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.",
"remediation": "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": {
"kind": "flow",
"name": "get_attachment → get_logs → check_imessage_availability"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"get_unread_messages",
"get_contact",
"search_attachments",
"get_attachment"
],
"sources": [
"get_logs"
],
"sinks": [
"send_message",
"get_last_send_error",
"request_restart",
"get_contact",
"resolve_conversation",
"check_imessage_availability"
],
"path": [
"get_attachment",
"get_logs",
"check_imessage_availability"
],
"edges": [
{
"from": "get_attachment",
"to": "get_logs",
"kind": "agent-mediated"
},
{
"from": "get_logs",
"to": "check_imessage_availability",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.js: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.",
"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": "dist/cli.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli.js",
"line": 8
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index-D8A4ss3o.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index-D8A4ss3o.js:960`): 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": "dist/index-D8A4ss3o.js"
},
"evidence": "exec(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index-D8A4ss3o.js",
"line": 960
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:2`): 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": "dist/index.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 2
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/media-intel-runtime-BkxG4bmW.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/media-intel-runtime-BkxG4bmW.js:4`): 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": "dist/media-intel-runtime-BkxG4bmW.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/media-intel-runtime-BkxG4bmW.js",
"line": 4
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/setup-wizard-22JoxToc.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/setup-wizard-22JoxToc.js:1`): 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": "dist/setup-wizard-22JoxToc.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/setup-wizard-22JoxToc.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shutdown-0TCv4XJB.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shutdown-0TCv4XJB.js:4`): 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": "dist/shutdown-0TCv4XJB.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shutdown-0TCv4XJB.js",
"line": 4
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tui.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tui.js:6`): 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": "dist/tui.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tui.js",
"line": 6
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (native/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`native/index.js:56`): 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": "native/index.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "native/index.js",
"line": 56
}
},
{
"ruleId": "MTC-INJ-TARGET-2",
"title": "Solicitation of model context / history",
"category": "injection",
"severity": "medium",
"confidence": "heuristic",
"description": "Solicitation of model context / history detected in the description of tool \"chat_analytics\". 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": "chat_analytics",
"field": "description"
},
"evidence": "chat history",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "sensitive-target"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (native/index.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`native/index.js:66`): 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.",
"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": "native/index.js"
},
"evidence": "require(process.env.NAPI_RS_NATIVE_LIBRARY_PATH)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "native/index.js",
"line": 66
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"get_unread_messages",
"get_contact",
"search_attachments",
"get_attachment"
],
"sensitiveSource": [
"get_logs"
],
"externalSink": [
"send_message",
"get_last_send_error",
"request_restart",
"get_contact",
"resolve_conversation",
"check_imessage_availability"
],
"selfContained": false,
"path": [
"get_attachment",
"get_logs",
"check_imessage_availability"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: get_attachment → get_logs → check_imessage_availability."
}
],
"capabilities": [
{
"tool": "get_messages",
"tags": [],
"reasons": {}
},
{
"tool": "export_messages",
"tags": [],
"reasons": {}
},
{
"tool": "get_unread_messages",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\"",
"parameter \"recipient\""
]
}
},
{
"tool": "wait_for_reply",
"tags": [],
"reasons": {}
},
{
"tool": "list_conversations",
"tags": [],
"reasons": {}
},
{
"tool": "search_messages",
"tags": [],
"reasons": {}
},
{
"tool": "get_logs",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_logs\""
]
}
},
{
"tool": "get_last_send_error",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "run_build",
"tags": [],
"reasons": {}
},
{
"tool": "request_restart",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"request\""
]
}
},
{
"tool": "health_check",
"tags": [],
"reasons": {}
},
{
"tool": "list_contacts",
"tags": [],
"reasons": {}
},
{
"tool": "search_contacts",
"tags": [],
"reasons": {}
},
{
"tool": "get_contact",
"tags": [
"untrusted-input",
"external-sink"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
],
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "resolve_conversation",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "resolve_handle",
"tags": [],
"reasons": {}
},
{
"tool": "check_imessage_availability",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "search_attachments",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "get_attachment",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "chat_analytics",
"tags": [],
"reasons": {}
},
{
"tool": "init_human",
"tags": [],
"reasons": {}
},
{
"tool": "All loaded contacts",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "4bac5eb8bdeb1e642605c40e27096d681cdd4ac47599a7bbf8d5ceacd7db0a04",
"stats": {
"tools": 23,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 8,
"medium": 2,
"low": 0,
"info": 0
}
}
}