Renef — 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": "renef-mcp",
"source": {
"kind": "package",
"origin": "renef-mcp"
},
"server": {
"name": "renef-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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"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"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (75 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 ([renef_memory_dump]) and tools that can send data out ([renef_exec, renef_spawn, renef_zero_copy_multiline_exec]) 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": "renef_memory_dump → renef_exec"
},
"evidence": "sources [renef_memory_dump] → sinks [renef_exec, renef_spawn, renef_zero_copy_multiline_exec]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"renef_memory_dump"
],
"sinks": [
"renef_exec",
"renef_spawn",
"renef_zero_copy_multiline_exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"renef_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"renef_exec\" appears to run shell commands or evaluate code (keyword \"exec\" 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": "renef_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"renef_spawn\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"renef_spawn\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "renef_spawn"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"renef_zero_copy_multiline_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"renef_zero_copy_multiline_exec\" appears to run shell commands or evaluate code (keyword \"exec\" 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": "renef_zero_copy_multiline_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tools/core/renef_hard_reset.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools/core/renef_hard_reset.py:12`): 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": "src/tools/core/renef_hard_reset.py"
},
"evidence": "ang\"\"\" try: subprocess.run([\"pkill\", \"-9\", \"adb\"], capture_output=True, timeout=5) except: pass",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tools/core/renef_hard_reset.py",
"line": 12,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tools/core/renef_spawn.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools/core/renef_spawn.py:11`): 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": "src/tools/core/renef_spawn.py"
},
"evidence": "kage name of the app to spawn (e.g., com.example.app) hook_type: Hooking mechanism - 'pltgot' for PLT/GOT hookin",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tools/core/renef_spawn.py",
"line": 11,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"renef_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"renef_exec\" 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": "renef_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"renef_spawn\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"renef_spawn\" 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": "renef_spawn"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"renef_zero_copy_multiline_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"renef_zero_copy_multiline_exec\" 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": "renef_zero_copy_multiline_exec"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"renef_memory_dump"
],
"externalSink": [
"renef_exec",
"renef_spawn",
"renef_zero_copy_multiline_exec"
],
"selfContained": false,
"path": [
"renef_memory_dump",
"renef_exec"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: renef_memory_dump → renef_exec."
}
],
"capabilities": [
{
"tool": "adb_current_app",
"tags": [],
"reasons": {}
},
{
"tool": "adb_devices",
"tags": [],
"reasons": {}
},
{
"tool": "adb_list_apps",
"tags": [],
"reasons": {}
},
{
"tool": "adb_root_status",
"tags": [],
"reasons": {}
},
{
"tool": "adb_selinux_disable",
"tags": [],
"reasons": {}
},
{
"tool": "adb_selinux_enable",
"tags": [],
"reasons": {}
},
{
"tool": "adb_selinux_status",
"tags": [],
"reasons": {}
},
{
"tool": "adb_start_app_am",
"tags": [],
"reasons": {}
},
{
"tool": "adb_start_app_monkey",
"tags": [],
"reasons": {}
},
{
"tool": "adb_stop_app_am",
"tags": [],
"reasons": {}
},
{
"tool": "renef_attach",
"tags": [],
"reasons": {}
},
{
"tool": "renef_cli_reset",
"tags": [],
"reasons": {}
},
{
"tool": "renef_console_log",
"tags": [],
"reasons": {}
},
{
"tool": "renef_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "renef_hard_reset",
"tags": [],
"reasons": {}
},
{
"tool": "renef_list_apps",
"tags": [],
"reasons": {}
},
{
"tool": "renef_load_script",
"tags": [],
"reasons": {}
},
{
"tool": "renef_ping",
"tags": [],
"reasons": {}
},
{
"tool": "renef_plugins",
"tags": [],
"reasons": {}
},
{
"tool": "renef_spawn",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "renef_thread_backtrace",
"tags": [],
"reasons": {}
},
{
"tool": "renef_thread_id",
"tags": [],
"reasons": {}
},
{
"tool": "renef_watch_realtime",
"tags": [],
"reasons": {}
},
{
"tool": "renef_zero_copy_multiline_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "run",
"tags": [],
"reasons": {}
},
{
"tool": "renef_file_exists",
"tags": [],
"reasons": {}
},
{
"tool": "renef_file_fdpath",
"tags": [],
"reasons": {}
},
{
"tool": "renef_file_read",
"tags": [],
"reasons": {}
},
{
"tool": "renef_file_readlink",
"tags": [],
"reasons": {}
},
{
"tool": "renef_hook_generate",
"tags": [],
"reasons": {}
},
{
"tool": "renef_hook_java",
"tags": [],
"reasons": {}
},
{
"tool": "renef_hook_native",
"tags": [],
"reasons": {}
},
{
"tool": "renef_hooks_list",
"tags": [],
"reasons": {}
},
{
"tool": "renef_unhook",
"tags": [],
"reasons": {}
},
{
"tool": "renef_watch",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_delete_ref",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_get_string",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_new_string",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_string_length",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_type_boolean",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_type_int",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_type_long",
"tags": [],
"reasons": {}
},
{
"tool": "renef_jni_type_string",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_read",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_read_u8",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_read_u16",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_read_u32",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_read_u64",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_read_string",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_search",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_search_json",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_write",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_write_u8",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_write_u16",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_write_u32",
"tags": [],
"reasons": {}
},
{
"tool": "renef_mem_write_u64",
"tags": [],
"reasons": {}
},
{
"tool": "renef_memory_dump",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"dump\""
]
}
},
{
"tool": "renef_memory_patch",
"tags": [],
"reasons": {}
},
{
"tool": "renef_detect_framework",
"tags": [],
"reasons": {}
},
{
"tool": "renef_module_exports",
"tags": [],
"reasons": {}
},
{
"tool": "renef_module_find",
"tags": [],
"reasons": {}
},
{
"tool": "renef_module_list",
"tags": [],
"reasons": {}
},
{
"tool": "renef_module_symbols",
"tags": [],
"reasons": {}
},
{
"tool": "renef_sections",
"tags": [],
"reasons": {}
},
{
"tool": "search_techniques",
"tags": [],
"reasons": {}
},
{
"tool": "renef_port_forward_add",
"tags": [],
"reasons": {}
},
{
"tool": "renef_port_forward_remove",
"tags": [],
"reasons": {}
},
{
"tool": "renef_port_forward_remove_all",
"tags": [],
"reasons": {}
},
{
"tool": "renef_port_forward_status",
"tags": [],
"reasons": {}
},
{
"tool": "renef_server_deploy",
"tags": [],
"reasons": {}
},
{
"tool": "renef_server_kill",
"tags": [],
"reasons": {}
},
{
"tool": "renef_server_logs",
"tags": [],
"reasons": {}
},
{
"tool": "renef_server_restart",
"tags": [],
"reasons": {}
},
{
"tool": "renef_server_start",
"tags": [],
"reasons": {}
},
{
"tool": "renef_server_status",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e034f005ac0d6641e49d3a243b470c3cd5801f22d2bb7266c7849555298b4f80",
"stats": {
"tools": 75,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 3,
"info": 0
}
}
}