Pepper Ios — 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": "pepper-ios",
"source": {
"kind": "package",
"origin": "pepper-ios"
},
"server": {
"name": "pepper-ios"
}
},
"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 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 (34 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 \"app_eval\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"app_eval\" appears to run shell commands or evaluate code (keyword \"eval\" 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": "app_eval"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/dylib_fetch.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/dylib_fetch.py:62`): 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": "pepper_ios/dylib_fetch.py"
},
"evidence": "rips signatures.\"\"\" subprocess.run( [\"codesign\", \"--force\", \"--sign\", \"-\", \"--deep\", str(framework_path)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/dylib_fetch.py",
"line": 62,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/mcp_build.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/mcp_build.py:108`): 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": "pepper_ios/mcp_build.py"
},
"evidence": "booted.\"\"\" result = subprocess.run([\"xcrun\", \"simctl\", \"list\", \"devices\", \"booted\", \"-j\"], capture_output=True, text",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/mcp_build.py",
"line": 108,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/mcp_eval_compiler.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/mcp_eval_compiler.py:61`): 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": "pepper_ios/mcp_eval_compiler.py"
},
"evidence": "itecture.\"\"\" arch = subprocess.check_output([\"uname\", \"-m\"]).decode().strip() sdk_name = \"iphonesimulator\" s",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/mcp_eval_compiler.py",
"line": 61,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/mcp_tools_dialog.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/mcp_tools_dialog.py:163`): 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": "pepper_ios/mcp_tools_dialog.py"
},
"evidence": "o_try: result = subprocess.run( [\"xcrun\", \"simctl\", \"privacy\", sim, \"grant\", perm, bid],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/mcp_tools_dialog.py",
"line": 163,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/mcp_tools_sim.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/mcp_tools_sim.py:109`): 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": "pepper_ios/mcp_tools_sim.py"
},
"evidence": "l\" result = subprocess.run([\"xcrun\", \"simctl\", \"install\", sim, app_path], capture_output=True, text=True)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/mcp_tools_sim.py",
"line": 109,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/pepper_ax.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/pepper_ax.py:192`): 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": "pepper_ios/pepper_ax.py"
},
"evidence": "try: result = subprocess.run( [\"pgrep\", \"-f\", \"Simulator.app/Contents/MacOS/Simulator\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/pepper_ax.py",
"line": 192,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/pepper_common.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/pepper_common.py:205`): 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": "pepper_ios/pepper_common.py"
},
"evidence": "try: proc = subprocess.Popen( [\"dns-sd\", \"-B\", \"_pepper._tcp.\", \"local.\"], stdout=su",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/pepper_common.py",
"line": 205,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/pepper_sessions.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/pepper_sessions.py:511`): 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": "pepper_ios/pepper_sessions.py"
},
"evidence": "ubprocess result = subprocess.run([\"xcrun\", \"simctl\", \"list\", \"devices\", \"booted\", \"-j\"], capture_output=True, text",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/pepper_sessions.py",
"line": 511,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/test_lifecycle.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/test_lifecycle.py:53`): 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": "pepper_ios/test_lifecycle.py"
},
"evidence": "urn code.\"\"\" return subprocess.run( cmd, capture_output=capture, text=True, timeout=timeout, check=c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/test_lifecycle.py",
"line": 53,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pepper_ios/test_runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pepper_ios/test_runner.py:285`): 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": "pepper_ios/test_runner.py"
},
"evidence": "try: result = subprocess.run( command, shell=True, capture_output=True, text=True, tim",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pepper_ios/test_runner.py",
"line": 285,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"app_eval\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"app_eval\" 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": "app_eval"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"pepper-ios\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "pepper-ios"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"pepper-ios\" 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": "pepper-ios"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "app_build_hw",
"tags": [],
"reasons": {}
},
{
"tool": "app_build",
"tags": [],
"reasons": {}
},
{
"tool": "app_automation",
"tags": [],
"reasons": {}
},
{
"tool": "app_debug",
"tags": [],
"reasons": {}
},
{
"tool": "app_perf",
"tags": [],
"reasons": {}
},
{
"tool": "app_swiftui",
"tags": [],
"reasons": {}
},
{
"tool": "app_console",
"tags": [],
"reasons": {}
},
{
"tool": "nav_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "ui_toggle",
"tags": [],
"reasons": {}
},
{
"tool": "app_eval",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "app_look",
"tags": [],
"reasons": {}
},
{
"tool": "ui_tap",
"tags": [],
"reasons": {}
},
{
"tool": "ui_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "ui_input",
"tags": [],
"reasons": {}
},
{
"tool": "nav_go",
"tags": [],
"reasons": {}
},
{
"tool": "nav_back",
"tags": [],
"reasons": {}
},
{
"tool": "nav_dismiss",
"tags": [],
"reasons": {}
},
{
"tool": "ui_swipe",
"tags": [],
"reasons": {}
},
{
"tool": "nav_screen",
"tags": [],
"reasons": {}
},
{
"tool": "nav_keyboard",
"tags": [],
"reasons": {}
},
{
"tool": "app_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "net_tools",
"tags": [],
"reasons": {}
},
{
"tool": "app_network",
"tags": [],
"reasons": {}
},
{
"tool": "app_record",
"tags": [],
"reasons": {}
},
{
"tool": "script",
"tags": [],
"reasons": {}
},
{
"tool": "sim_raw",
"tags": [],
"reasons": {}
},
{
"tool": "sim_control",
"tags": [],
"reasons": {}
},
{
"tool": "state_vars",
"tags": [],
"reasons": {}
},
{
"tool": "state_tools",
"tags": [],
"reasons": {}
},
{
"tool": "sys_tools",
"tags": [],
"reasons": {}
},
{
"tool": "app_status",
"tags": [],
"reasons": {}
},
{
"tool": "ui_gesture",
"tags": [],
"reasons": {}
},
{
"tool": "ui_accessibility",
"tags": [],
"reasons": {}
},
{
"tool": "ui_query",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "cfa987fc6465887b03e15c3dde2a2f6361e1d06dedd16731c4e7bf898fea4e29",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 11,
"medium": 0,
"low": 1,
"info": 2
}
}
}