Android Dev — 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": "@maheshmishra271090-design/android-dev-mcp",
"source": {
"kind": "package",
"origin": "@maheshmishra271090-design/android-dev-mcp"
},
"server": {
"name": "@maheshmishra271090-design/android-dev-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": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (24 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_android_cli\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_android_cli\" 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": "run_android_cli"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_adb\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_adb\" 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": "run_adb"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_git\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_git\" 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": "run_git"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_gradle\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_gradle\" 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": "run_gradle"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_bash\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_bash\" appears to run shell commands or evaluate code (keyword \"bash\" in tool name, 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": "run_bash"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/cli.js:2`): 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": "bin/cli.js"
},
"evidence": "{ execSync } = require(\"child_process\"); const fs = require(\"fs\"); const path = require(\"path\"); const os = require(\"os\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/cli.js",
"line": 2,
"nonRuntime": false
}
},
{
"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:41`): 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": "require(\"path\")); const child_process_1 = require(\"child_process\"); const KNOWLEDGE_DIR = path.join(__dirname, \"../knowl",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 41,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_android_cli\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_android_cli\" 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": "run_android_cli",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_adb\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_adb\" 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": "run_adb",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_git\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_git\" 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": "run_git",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_gradle\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_gradle\" 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": "run_gradle",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_bash\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_bash\" 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": "run_bash",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (bin/cli.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`bin/cli.js:87`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "bin/cli.js"
},
"evidence": "ommand === \"start\") { require(SERVER_ENTRY); } else if (command === \"setup-claude-md\") { // Optional --dir flag: an",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "bin/cli.js",
"line": 87,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_android_cli\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_android_cli\" 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_android_cli"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_adb\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_adb\" 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_adb"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_git\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_git\" 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_git"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_gradle\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_gradle\" 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_gradle"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_bash\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_bash\" 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_bash"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_full_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_project_structure",
"tags": [],
"reasons": {}
},
{
"tool": "get_architecture_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "get_ui_compose_standards",
"tags": [],
"reasons": {}
},
{
"tool": "get_api_backend_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "get_player_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "get_cicd_commands",
"tags": [],
"reasons": {}
},
{
"tool": "check_ui_fluidity",
"tags": [],
"reasons": {}
},
{
"tool": "generate_tests",
"tags": [],
"reasons": {}
},
{
"tool": "get_git_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "get_prompt_templates",
"tags": [],
"reasons": {}
},
{
"tool": "get_session_hygiene",
"tags": [],
"reasons": {}
},
{
"tool": "get_model_routing",
"tags": [],
"reasons": {}
},
{
"tool": "get_tooling_setup",
"tags": [],
"reasons": {}
},
{
"tool": "get_android_cli_guide",
"tags": [],
"reasons": {}
},
{
"tool": "run_android_cli",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "run_adb",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "run_git",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "run_gradle",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "run_bash",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"bash\" in tool name",
"parameter \"command\""
]
}
},
{
"tool": "get_live_versions",
"tags": [],
"reasons": {}
},
{
"tool": "scaffold_feature",
"tags": [],
"reasons": {}
},
{
"tool": "verify_ui",
"tags": [],
"reasons": {}
},
{
"tool": "fluidity_debug_workflow",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "3a9e5460f291ae38f096717e455beb0048b4e125b3f3ec0610fe8b721b520c6a",
"stats": {
"tools": 24,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 6,
"low": 5,
"info": 0
}
}
}