Lamina — the complete, unedited output of the deterministic mcptrustchecker engine v1.12.1, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.12.1",
"methodologyVersion": "mcptrustchecker-1.12"
},
"target": {
"id": "https://app.uselamina.ai/mcp/agent",
"source": {
"kind": "http",
"origin": "https://app.uselamina.ai/mcp/agent"
},
"server": {
"name": "lamina-creative-studio",
"version": "1.0.0"
}
},
"grade": "B",
"score": {
"score": 88,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 6.3,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-CAP-003",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "live",
"label": "inspection depth (live) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.12"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "live",
"inputs": {
"toolSurface": true,
"implementationSource": false,
"packageMetadata": false,
"liveTransport": true
},
"caveats": []
},
"findings": [
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"lamina_compose_video\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"lamina_compose_video\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "lamina_compose_video"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"lamina_compose_plan\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"lamina_compose_plan\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "lamina_compose_plan"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-003",
"title": "Annotation contradicts behavior on \"lamina_compose_plan\"",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"lamina_compose_plan\" advertises readOnlyHint=true but its derived capabilities include state-modifying actions (code-exec). Tool annotations are attacker-controllable and must never be trusted; a mismatch like this is exactly how a hostile server hides a destructive tool.",
"remediation": "Ignore server-provided annotations for security decisions; gate destructive tools on explicit user consent.",
"location": {
"kind": "tool",
"name": "lamina_compose_plan"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"tags": [
"code-exec"
],
"annotations": {
"title": "Plan a narrated video (dry run)",
"readOnlyHint": true
}
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"lamina_compose_video\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"lamina_compose_video\" takes a command-shaped parameter \"script\" 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": "lamina_compose_video",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"lamina_compose_plan\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"lamina_compose_plan\" takes a command-shaped parameter \"script\" 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": "lamina_compose_plan",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"lamina_compose_video\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"lamina_compose_video\" 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": "lamina_compose_video"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"lamina_compose_plan\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"lamina_compose_plan\" 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": "lamina_compose_plan"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-NET-005",
"title": "Remote HTTP MCP endpoint",
"category": "network",
"severity": "info",
"confidence": "strong",
"description": "Remote endpoint app.uselamina.ai. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
"location": {
"kind": "transport"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "lamina_discover",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_describe",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_run",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_status",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_models_list",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_models_describe",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_generate_image",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_generate_video",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_plv_background",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_generate_hook",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_compose_video",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "lamina_compose_formats",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_compose_plan",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "lamina_brand",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_brand_kit",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_set_brand_kit_element",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_save_to_brand_kit",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_upload_asset",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_cancel",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_create",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_generate_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_app_versions",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_set_visibility",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_set_brand",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_brand_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_brand_compliance",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_brand_score",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_refine_to_brand",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_credits",
"tags": [],
"reasons": {}
},
{
"tool": "lamina_topup",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "f15205ba004f77e8f9c290a6810be597a7579c41f50d7112137c5866660877cf",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 3,
"low": 2,
"info": 1
}
}
}