Usagi Game — 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": "usagi-game-mcp",
"source": {
"kind": "package",
"origin": "usagi-game-mcp"
},
"server": {
"name": "usagi-game-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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 create, modify or delete files",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"sensitive-source",
"file-write"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (22 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-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([usagi_read_file, usagi_list_files]) and tools that can send data out ([usagi_write_web_shell]) are exposed together. An agent can move private data to the sink.",
"remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
"location": {
"kind": "flow",
"name": "usagi_read_file → usagi_write_web_shell"
},
"evidence": "sources [usagi_read_file, usagi_list_files] → sinks [usagi_write_web_shell]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"usagi_read_file",
"usagi_list_files"
],
"sinks": [
"usagi_write_web_shell"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"usagi_write_web_shell\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"usagi_write_web_shell\" appears to run shell commands or evaluate code (keyword \"shell\" 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": "usagi_write_web_shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/dev/dev-process-manager.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/dev/dev-process-manager.js:179`): 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/dev/dev-process-manager.js"
},
"evidence": "']; const pty = spawn(shell, args, { cwd: projectPath, env: filteredEnv, col",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/dev/dev-process-manager.js",
"line": 179,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/sandbox/lua-binary.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/sandbox/lua-binary.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/sandbox/lua-binary.js"
},
"evidence": "port { execFile } from 'child_process'; import { promisify } from 'util'; const execFileAsync = promisify(execFile); con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/sandbox/lua-binary.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/sandbox/lua-runner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/sandbox/lua-runner.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/sandbox/lua-runner.js"
},
"evidence": "port { execFile } from 'child_process'; import * as fs from 'fs/promises'; import * as path from 'path'; import * as os",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/sandbox/lua-runner.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/scaffold-tools.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/scaffold-tools.js:173`): 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/tools/scaffold-tools.js"
},
"evidence": "} = await import('node:child_process'); const { promisify } = await import('node:util'); const execP =",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/scaffold-tools.js",
"line": 173,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"usagi_delete_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"usagi_delete_file\" can write, overwrite or delete files (keyword \"delete_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "usagi_delete_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"usagi_write_web_shell\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"usagi_write_web_shell\" 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": "usagi_write_web_shell"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"usagi_delete_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"usagi_delete_file\" 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": "usagi_delete_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"usagi-game-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "usagi-game-mcp"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"usagi-game-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "usagi-game-mcp"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"usagi_read_file",
"usagi_list_files"
],
"externalSink": [
"usagi_write_web_shell"
],
"selfContained": false,
"path": [
"usagi_list_files",
"usagi_write_web_shell"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: usagi_list_files → usagi_write_web_shell."
}
],
"capabilities": [
{
"tool": "usagi_dev_start",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_dev_stop",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_dev_restart",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_dev_status",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_dev_reset",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_read_log",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_boot_test",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_write_lua",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_write_config",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_write_data",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_write_web_shell",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\" in tool name"
]
}
},
{
"tool": "usagi_read_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "usagi_list_files",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "usagi_delete_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"delete_file\" in tool name"
]
}
},
{
"tool": "usagi_rename_file",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_init_project",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_scaffold_entity",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_scaffold_state",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_scaffold_state_machine",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_scaffold_collision_handler",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_scaffold_save_system",
"tags": [],
"reasons": {}
},
{
"tool": "usagi_validate_project",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "4a254208f48c7792dfa92371dc528fa11ba49223b93edbce0aa880980f7e2ba4",
"stats": {
"tools": 22,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 1,
"low": 2,
"info": 2
}
}
}