Hyperpanes — 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": "hyperpanes-mcp",
"source": {
"kind": "package",
"origin": "hyperpanes-mcp"
},
"server": {
"name": "hyperpanes-mcp"
}
},
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (45 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 \"open_pane\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"open_pane\" appears to run shell commands or evaluate code (parameter \"command\"). 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": "open_pane"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"spawn_workers\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_workers\" 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_workers"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/backlog/sources.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/backlog/sources.js:13`): 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/backlog/sources.js"
},
"evidence": "{ execFile } from 'node:child_process'; import { promisify } from 'node:util'; const execFileP = promisify(execFile); co",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/backlog/sources.js",
"line": 13,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launch.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launch.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/launch.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { mkdtempSync, writeFileSync } from 'node:fs'; import { tmpdir } from 'no",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launch.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/worker-pool/git.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/worker-pool/git.js:7`): 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/worker-pool/git.js"
},
"evidence": "{ execFile } from 'node:child_process'; import { promisify } from 'node:util'; const execFileP = promisify(execFile); ex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/worker-pool/git.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/worker-pool/review.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/worker-pool/review.js:20`): 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/worker-pool/review.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { Git } from './git.js'; /** Default review budget if the controller does",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/worker-pool/review.js",
"line": 20,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/worker-pool/worker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/worker-pool/worker.js: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": "dist/worker-pool/worker.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { readFileSync, writeFileSync, existsSync, rmSync } from 'node:fs'; impor",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/worker-pool/worker.js",
"line": 23,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([read_pane, read_messages, send_message, get_task]) co-exist with external-action tools ([open_pane, spawn_workers, send_message]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "read_pane → open_pane"
},
"evidence": "untrusted [read_pane, read_messages, send_message, get_task] → sinks [open_pane, spawn_workers, send_message]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"read_pane",
"read_messages",
"send_message",
"get_task"
],
"sinks": [
"open_pane",
"spawn_workers",
"send_message"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"open_pane\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"open_pane\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "open_pane",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"shell\" on \"open_pane\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"open_pane\" takes a command-shaped parameter \"shell\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "open_pane",
"field": "inputSchema.properties.shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "shell"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"open_pane\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"open_pane\" 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": "open_pane"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_workers\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_workers\" 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_workers"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"read_pane",
"read_messages",
"send_message",
"get_task"
],
"sensitiveSource": [],
"externalSink": [
"open_pane",
"spawn_workers",
"send_message"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "control_status",
"tags": [],
"reasons": {}
},
{
"tool": "list_panes",
"tags": [],
"reasons": {}
},
{
"tool": "read_pane",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "open_pane",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "spawn_workers",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "open_tab",
"tags": [],
"reasons": {}
},
{
"tool": "list_projects",
"tags": [],
"reasons": {}
},
{
"tool": "add_project",
"tags": [],
"reasons": {}
},
{
"tool": "rename_project",
"tags": [],
"reasons": {}
},
{
"tool": "recolor_project",
"tags": [],
"reasons": {}
},
{
"tool": "remove_project",
"tags": [],
"reasons": {}
},
{
"tool": "set_meta",
"tags": [],
"reasons": {}
},
{
"tool": "set_layout",
"tags": [],
"reasons": {}
},
{
"tool": "restart_pane",
"tags": [],
"reasons": {}
},
{
"tool": "queue_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "restart_app",
"tags": [],
"reasons": {}
},
{
"tool": "rename_pane",
"tags": [],
"reasons": {}
},
{
"tool": "recolor_pane",
"tags": [],
"reasons": {}
},
{
"tool": "send_input",
"tags": [],
"reasons": {}
},
{
"tool": "send_keys",
"tags": [],
"reasons": {}
},
{
"tool": "prompt_pane",
"tags": [],
"reasons": {}
},
{
"tool": "set_talk",
"tags": [],
"reasons": {}
},
{
"tool": "set_speech",
"tags": [],
"reasons": {}
},
{
"tool": "stop_speech",
"tags": [],
"reasons": {}
},
{
"tool": "whoami",
"tags": [],
"reasons": {}
},
{
"tool": "read_messages",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "send_message",
"tags": [
"untrusted-input",
"external-sink"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
],
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "send_to_parent",
"tags": [],
"reasons": {}
},
{
"tool": "broadcast_subtree",
"tags": [],
"reasons": {}
},
{
"tool": "mint_token",
"tags": [],
"reasons": {}
},
{
"tool": "lock_pane",
"tags": [],
"reasons": {}
},
{
"tool": "unlock_pane",
"tags": [],
"reasons": {}
},
{
"tool": "list_queues",
"tags": [],
"reasons": {}
},
{
"tool": "enqueue_task",
"tags": [],
"reasons": {}
},
{
"tool": "claim_task",
"tags": [],
"reasons": {}
},
{
"tool": "ack_task",
"tags": [],
"reasons": {}
},
{
"tool": "nack_task",
"tags": [],
"reasons": {}
},
{
"tool": "extend_task",
"tags": [],
"reasons": {}
},
{
"tool": "get_task",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "list_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "purge_queue",
"tags": [],
"reasons": {}
},
{
"tool": "list_layouts",
"tags": [],
"reasons": {}
},
{
"tool": "validate_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "build_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "launch_workspace",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c2a7d01604d535e99b981572eef3801236cbb9e14c2ac409ebaef2cc84ef5e6d",
"stats": {
"tools": 45,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 3,
"low": 2,
"info": 0
}
}
}