Linkedsword — 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": "linkedsword-mcp",
"source": {
"kind": "package",
"origin": "linkedsword-mcp"
},
"server": {
"name": "linkedsword-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": [
"code-exec",
"untrusted-input",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (93 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 \"run_code\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_code\" appears to run shell commands or evaluate code (keyword \"run_code\" 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": "run_code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_script_in_play_mode\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_script_in_play_mode\" appears to run shell commands or evaluate code (keyword \"run_script\" 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": "run_script_in_play_mode"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([list_library, get_asset_details, get_plan]) co-exist with external-action tools ([run_code, run_script_in_play_mode]). 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": "list_library → run_code"
},
"evidence": "untrusted [list_library, get_asset_details, get_plan] → sinks [run_code, run_script_in_play_mode]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"list_library",
"get_asset_details",
"get_plan"
],
"sinks": [
"run_code",
"run_script_in_play_mode"
]
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/index.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:2461`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "const res2 = await fetch(\"https://apis.roblox.com/assets/v1/assets\", { method: \"POST\", headers: { \"",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/index.js",
"line": 2461,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"code\" on \"run_code\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_code\" takes a command-shaped parameter \"code\" 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": "run_code",
"field": "inputSchema.properties.code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "code"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"code\" on \"run_script_in_play_mode\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_script_in_play_mode\" takes a command-shaped parameter \"code\" 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": "run_script_in_play_mode",
"field": "inputSchema.properties.code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "code"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_code\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_code\" 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": "run_code"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_script_in_play_mode\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_script_in_play_mode\" 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": "run_script_in_play_mode"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/install-plugin.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/install-plugin.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": "scripts/install-plugin.js"
},
"evidence": "ecFileSync } = require(\"child_process\"); // Try the bundled location first (npm install), then fall back to the dev //",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/install-plugin.js",
"line": 7,
"nonRuntime": true
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"list_library",
"get_asset_details",
"get_plan"
],
"sensitiveSource": [],
"externalSink": [
"run_code",
"run_script_in_play_mode"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "get_file_tree",
"tags": [],
"reasons": {}
},
{
"tool": "get_project_structure",
"tags": [],
"reasons": {}
},
{
"tool": "get_place_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_services",
"tags": [],
"reasons": {}
},
{
"tool": "list_roblox_studios",
"tags": [],
"reasons": {}
},
{
"tool": "set_active_studio",
"tags": [],
"reasons": {}
},
{
"tool": "search_files",
"tags": [],
"reasons": {}
},
{
"tool": "search_objects",
"tags": [],
"reasons": {}
},
{
"tool": "search_by_property",
"tags": [],
"reasons": {}
},
{
"tool": "get_instance_properties",
"tags": [],
"reasons": {}
},
{
"tool": "get_instance_children",
"tags": [],
"reasons": {}
},
{
"tool": "get_class_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_selection",
"tags": [],
"reasons": {}
},
{
"tool": "grep_scripts",
"tags": [],
"reasons": {}
},
{
"tool": "mass_get_property",
"tags": [],
"reasons": {}
},
{
"tool": "set_selection",
"tags": [],
"reasons": {}
},
{
"tool": "get_descendants",
"tags": [],
"reasons": {}
},
{
"tool": "get_stable_id",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_stable_id",
"tags": [],
"reasons": {}
},
{
"tool": "compare_instances",
"tags": [],
"reasons": {}
},
{
"tool": "get_connected_instances",
"tags": [],
"reasons": {}
},
{
"tool": "parallel_search",
"tags": [],
"reasons": {}
},
{
"tool": "get_script_source",
"tags": [],
"reasons": {}
},
{
"tool": "set_script_source",
"tags": [],
"reasons": {}
},
{
"tool": "patch_script",
"tags": [],
"reasons": {}
},
{
"tool": "grep_replace",
"tags": [],
"reasons": {}
},
{
"tool": "execute_luau",
"tags": [],
"reasons": {}
},
{
"tool": "run_code",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_code\" in tool name"
]
}
},
{
"tool": "edit_script_lines",
"tags": [],
"reasons": {}
},
{
"tool": "insert_script_lines",
"tags": [],
"reasons": {}
},
{
"tool": "delete_script_lines",
"tags": [],
"reasons": {}
},
{
"tool": "create_object",
"tags": [],
"reasons": {}
},
{
"tool": "delete_object",
"tags": [],
"reasons": {}
},
{
"tool": "set_property",
"tags": [],
"reasons": {}
},
{
"tool": "mass_create_objects",
"tags": [],
"reasons": {}
},
{
"tool": "mass_set_property",
"tags": [],
"reasons": {}
},
{
"tool": "mass_duplicate",
"tags": [],
"reasons": {}
},
{
"tool": "smart_duplicate",
"tags": [],
"reasons": {}
},
{
"tool": "set_calculated_property",
"tags": [],
"reasons": {}
},
{
"tool": "clone_object",
"tags": [],
"reasons": {}
},
{
"tool": "reparent_object",
"tags": [],
"reasons": {}
},
{
"tool": "group_objects",
"tags": [],
"reasons": {}
},
{
"tool": "ungroup_objects",
"tags": [],
"reasons": {}
},
{
"tool": "batch_operations",
"tags": [],
"reasons": {}
},
{
"tool": "start_playtest",
"tags": [],
"reasons": {}
},
{
"tool": "stop_playtest",
"tags": [],
"reasons": {}
},
{
"tool": "get_playtest_output",
"tags": [],
"reasons": {}
},
{
"tool": "get_studio_mode",
"tags": [],
"reasons": {}
},
{
"tool": "run_script_in_play_mode",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_script\" in tool name"
]
}
},
{
"tool": "user_mouse_input",
"tags": [],
"reasons": {}
},
{
"tool": "user_keyboard_input",
"tags": [],
"reasons": {}
},
{
"tool": "character_navigation",
"tags": [],
"reasons": {}
},
{
"tool": "run_playtest_scenario",
"tags": [],
"reasons": {}
},
{
"tool": "get_diff_queue",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_diff",
"tags": [],
"reasons": {}
},
{
"tool": "get_diff_history",
"tags": [],
"reasons": {}
},
{
"tool": "get_activity_log",
"tags": [],
"reasons": {}
},
{
"tool": "set_mode",
"tags": [],
"reasons": {}
},
{
"tool": "rollback",
"tags": [],
"reasons": {}
},
{
"tool": "get_attribute",
"tags": [],
"reasons": {}
},
{
"tool": "get_attributes",
"tags": [],
"reasons": {}
},
{
"tool": "get_tags",
"tags": [],
"reasons": {}
},
{
"tool": "get_tagged",
"tags": [],
"reasons": {}
},
{
"tool": "capture_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "export_build",
"tags": [],
"reasons": {}
},
{
"tool": "import_build",
"tags": [],
"reasons": {}
},
{
"tool": "list_library",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "insert_model",
"tags": [],
"reasons": {}
},
{
"tool": "set_attribute",
"tags": [],
"reasons": {}
},
{
"tool": "delete_attribute",
"tags": [],
"reasons": {}
},
{
"tool": "add_tag",
"tags": [],
"reasons": {}
},
{
"tool": "remove_tag",
"tags": [],
"reasons": {}
},
{
"tool": "redo",
"tags": [],
"reasons": {}
},
{
"tool": "set_auto_accept",
"tags": [],
"reasons": {}
},
{
"tool": "get_auto_accept_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_console_output",
"tags": [],
"reasons": {}
},
{
"tool": "create_weld",
"tags": [],
"reasons": {}
},
{
"tool": "get_bounding_box",
"tags": [],
"reasons": {}
},
{
"tool": "raycast",
"tags": [],
"reasons": {}
},
{
"tool": "fill_terrain",
"tags": [],
"reasons": {}
},
{
"tool": "clear_terrain",
"tags": [],
"reasons": {}
},
{
"tool": "upload_asset",
"tags": [],
"reasons": {}
},
{
"tool": "search_assets",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_details",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "get_asset_thumbnail",
"tags": [],
"reasons": {}
},
{
"tool": "create_plan",
"tags": [],
"reasons": {}
},
{
"tool": "get_plan",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "list_plans",
"tags": [],
"reasons": {}
},
{
"tool": "update_plan_step",
"tags": [],
"reasons": {}
},
{
"tool": "delete_plan",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "revert_to_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "delete_checkpoint",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "399065d22b3c5555a20b0e3e54531923b19cdde314d80145f55af8d2ddfd416b",
"stats": {
"tools": 93,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 4,
"low": 3,
"info": 0
}
}
}