Robloxstudio Mcp Remake — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "robloxstudio-mcp-remake",
"source": {
"kind": "package",
"origin": "robloxstudio-mcp-remake"
},
"server": {
"name": "robloxstudio-mcp-remake"
}
},
"grade": "B",
"score": {
"score": 87,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"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": "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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"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 (96 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_tests\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_tests\" 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": "run_tests"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"map_dependencies\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"map_dependencies\" 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": "map_dependencies"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"find_variable_leaks\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"find_variable_leaks\" 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": "find_variable_leaks"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"insert_comments\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"insert_comments\" 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": "insert_comments"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"generate_script\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"generate_script\" 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": "generate_script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"build_context\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"build_context\" 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": "build_context"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"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: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/index.js"
},
"evidence": "; import { exec } from \"child_process\"; import path3 from \"path\"; import { fileURLToPath as fileURLToPath3 } from \"url\";",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 7,
"nonRuntime": false
}
},
{
"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:3671`): 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 csrfRes = await fetch(\"https://auth.roblox.com/v2/logout\", { method: \"POST\", headers: { \"Cookie\": `.",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/index.js",
"line": 3671,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/index.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:6401`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "en\" : \"xdg-open\"; exec(`${startCmd} \"\" \"${dashboardUrl}\"`, (err) => { if (err) console.error(\"Fa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/index.js",
"line": 6401,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_path\" on \"run_tests\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_tests\" takes a command-shaped parameter \"script_path\" 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_tests",
"field": "inputSchema.properties.script_path"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_path"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_path\" on \"map_dependencies\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"map_dependencies\" takes a command-shaped parameter \"script_path\" 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": "map_dependencies",
"field": "inputSchema.properties.script_path"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_path"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_path\" on \"find_variable_leaks\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"find_variable_leaks\" takes a command-shaped parameter \"script_path\" 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": "find_variable_leaks",
"field": "inputSchema.properties.script_path"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_path"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_path\" on \"insert_comments\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"insert_comments\" takes a command-shaped parameter \"script_path\" 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": "insert_comments",
"field": "inputSchema.properties.script_path"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_path"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_name\" on \"generate_script\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"generate_script\" takes a command-shaped parameter \"script_name\" 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": "generate_script",
"field": "inputSchema.properties.script_name"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_name"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_path\" on \"build_context\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"build_context\" takes a command-shaped parameter \"script_path\" 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": "build_context",
"field": "inputSchema.properties.script_path"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_path"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_tests\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_tests\" 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_tests"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"map_dependencies\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"map_dependencies\" 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": "map_dependencies"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"find_variable_leaks\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"find_variable_leaks\" 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": "find_variable_leaks"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"insert_comments\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"insert_comments\" 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": "insert_comments"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"generate_script\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_script\" 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": "generate_script"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"build_context\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"build_context\" 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": "build_context"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_file_tree",
"tags": [],
"reasons": {}
},
{
"tool": "get_tree_path",
"tags": [],
"reasons": {}
},
{
"tool": "search_files",
"tags": [],
"reasons": {}
},
{
"tool": "get_place_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_services",
"tags": [],
"reasons": {}
},
{
"tool": "search_objects",
"tags": [],
"reasons": {}
},
{
"tool": "get_instance_properties",
"tags": [],
"reasons": {}
},
{
"tool": "get_instance_children",
"tags": [],
"reasons": {}
},
{
"tool": "get_instance_children_path",
"tags": [],
"reasons": {}
},
{
"tool": "search_by_property",
"tags": [],
"reasons": {}
},
{
"tool": "get_class_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_project_structure",
"tags": [],
"reasons": {}
},
{
"tool": "set_property",
"tags": [],
"reasons": {}
},
{
"tool": "mass_set_property",
"tags": [],
"reasons": {}
},
{
"tool": "mass_get_property",
"tags": [],
"reasons": {}
},
{
"tool": "create_object",
"tags": [],
"reasons": {}
},
{
"tool": "mass_create_objects",
"tags": [],
"reasons": {}
},
{
"tool": "delete_object",
"tags": [],
"reasons": {}
},
{
"tool": "smart_duplicate",
"tags": [],
"reasons": {}
},
{
"tool": "mass_duplicate",
"tags": [],
"reasons": {}
},
{
"tool": "get_script_source",
"tags": [],
"reasons": {}
},
{
"tool": "set_script_source",
"tags": [],
"reasons": {}
},
{
"tool": "edit_script_lines",
"tags": [],
"reasons": {}
},
{
"tool": "insert_script_lines",
"tags": [],
"reasons": {}
},
{
"tool": "delete_script_lines",
"tags": [],
"reasons": {}
},
{
"tool": "get_attribute",
"tags": [],
"reasons": {}
},
{
"tool": "set_attribute",
"tags": [],
"reasons": {}
},
{
"tool": "get_attributes",
"tags": [],
"reasons": {}
},
{
"tool": "delete_attribute",
"tags": [],
"reasons": {}
},
{
"tool": "get_tags",
"tags": [],
"reasons": {}
},
{
"tool": "add_tag",
"tags": [],
"reasons": {}
},
{
"tool": "remove_tag",
"tags": [],
"reasons": {}
},
{
"tool": "get_tagged",
"tags": [],
"reasons": {}
},
{
"tool": "get_selection",
"tags": [],
"reasons": {}
},
{
"tool": "execute_luau",
"tags": [],
"reasons": {}
},
{
"tool": "grep_scripts",
"tags": [],
"reasons": {}
},
{
"tool": "start_playtest",
"tags": [],
"reasons": {}
},
{
"tool": "stop_playtest",
"tags": [],
"reasons": {}
},
{
"tool": "get_playtest_output",
"tags": [],
"reasons": {}
},
{
"tool": "undo",
"tags": [],
"reasons": {}
},
{
"tool": "redo",
"tags": [],
"reasons": {}
},
{
"tool": "export_build",
"tags": [],
"reasons": {}
},
{
"tool": "create_build",
"tags": [],
"reasons": {}
},
{
"tool": "generate_build",
"tags": [],
"reasons": {}
},
{
"tool": "import_build",
"tags": [],
"reasons": {}
},
{
"tool": "list_library",
"tags": [],
"reasons": {}
},
{
"tool": "search_materials",
"tags": [],
"reasons": {}
},
{
"tool": "get_build",
"tags": [],
"reasons": {}
},
{
"tool": "import_scene",
"tags": [],
"reasons": {}
},
{
"tool": "search_assets",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_thumbnail",
"tags": [],
"reasons": {}
},
{
"tool": "preview_asset",
"tags": [],
"reasons": {}
},
{
"tool": "capture_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "capture_viewport",
"tags": [],
"reasons": {}
},
{
"tool": "insert_asset",
"tags": [],
"reasons": {}
},
{
"tool": "history_control",
"tags": [],
"reasons": {}
},
{
"tool": "control_selection",
"tags": [],
"reasons": {}
},
{
"tool": "validate_pathfinding",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_performance",
"tags": [],
"reasons": {}
},
{
"tool": "check_collisions",
"tags": [],
"reasons": {}
},
{
"tool": "manage_datastore",
"tags": [],
"reasons": {}
},
{
"tool": "build_library",
"tags": [],
"reasons": {}
},
{
"tool": "run_tests",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "generate_terrain",
"tags": [],
"reasons": {}
},
{
"tool": "control_lighting",
"tags": [],
"reasons": {}
},
{
"tool": "sync_project",
"tags": [],
"reasons": {}
},
{
"tool": "control_audio_animation",
"tags": [],
"reasons": {}
},
{
"tool": "monitor_remotes",
"tags": [],
"reasons": {}
},
{
"tool": "map_dependencies",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "find_variable_leaks",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "scan_anticheat",
"tags": [],
"reasons": {}
},
{
"tool": "auto_place",
"tags": [],
"reasons": {}
},
{
"tool": "mirror_instances",
"tags": [],
"reasons": {}
},
{
"tool": "snap_to_grid",
"tags": [],
"reasons": {}
},
{
"tool": "paint_surfaces",
"tags": [],
"reasons": {}
},
{
"tool": "track_changes",
"tags": [],
"reasons": {}
},
{
"tool": "manage_backups",
"tags": [],
"reasons": {}
},
{
"tool": "insert_comments",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "fix_naming",
"tags": [],
"reasons": {}
},
{
"tool": "build_cutscene",
"tags": [],
"reasons": {}
},
{
"tool": "simulate_physics",
"tags": [],
"reasons": {}
},
{
"tool": "generate_script",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "diff_instances",
"tags": [],
"reasons": {}
},
{
"tool": "build_context",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "batch_execute",
"tags": [],
"reasons": {}
},
{
"tool": "bulk_get_scripts",
"tags": [],
"reasons": {}
},
{
"tool": "bulk_set_properties",
"tags": [],
"reasons": {}
},
{
"tool": "manage_places",
"tags": [],
"reasons": {}
},
{
"tool": "build_ui",
"tags": [],
"reasons": {}
},
{
"tool": "capture_ui",
"tags": [],
"reasons": {}
},
{
"tool": "get_ui_templates",
"tags": [],
"reasons": {}
},
{
"tool": "sync_project_enhanced",
"tags": [],
"reasons": {}
},
{
"tool": "generate_test_report",
"tags": [],
"reasons": {}
},
{
"tool": "check_ui_design",
"tags": [],
"reasons": {}
},
{
"tool": "roblox_studio_workflow",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "32a11b39964bf7bbc7e7af4c8904333d2083b1540ea0ca861e79a2712f1ee54e",
"stats": {
"tools": 96,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 8,
"low": 6,
"info": 0
}
}
}