Clouvel — 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": "clouvel",
"source": {
"kind": "package",
"origin": "clouvel"
},
"server": {
"name": "clouvel"
}
},
"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": [
"can send data / act on an external service",
"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",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (88 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 ([list_files]) and tools that can send data out ([spawn_explore, spawn_librarian]) 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": "list_files → spawn_explore"
},
"evidence": "sources [list_files] → sinks [spawn_explore, spawn_librarian]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"list_files"
],
"sinks": [
"spawn_explore",
"spawn_librarian"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"spawn_explore\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_explore\" 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": "spawn_explore"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"spawn_librarian\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_librarian\" 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": "spawn_librarian"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/clouvel/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/cli.py:202`): 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/clouvel/cli.py"
},
"evidence": "check_result = subprocess.run( [\"claude\", \"mcp\", \"list\"], capture_output=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/clouvel/cli.py",
"line": 202,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/clouvel/tools/architecture.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/tools/architecture.py:69`): 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/clouvel/tools/architecture.py"
},
"evidence": "색 grep_result = subprocess.run( [\"grep\", \"-rn\", f\"(def|class) {name}\", str(project_path / \"src\")],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/clouvel/tools/architecture.py",
"line": 69,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/clouvel/tools/checkpoint.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/tools/checkpoint.py:44`): 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/clouvel/tools/checkpoint.py"
},
"evidence": "name branch = subprocess.run( [\"git\", \"rev-parse\", \"--abbrev-ref\", \"HEAD\"], capture_",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/clouvel/tools/checkpoint.py",
"line": 44,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/clouvel/tools/core.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/tools/core.py:266`): 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/clouvel/tools/core.py"
},
"evidence": "new) result = subprocess.run( [\"git\", \"diff\", \"--name-only\", \"--diff-filter=A\", \"HEAD\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/clouvel/tools/core.py",
"line": 266,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/clouvel/tools/install.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/tools/install.py:34`): 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/clouvel/tools/install.py"
},
"evidence": "try: result = subprocess.run( [\"claude\", \"--version\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/clouvel/tools/install.py",
"line": 34,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/clouvel/tools/ship_pro.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/tools/ship_pro.py:242`): 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/clouvel/tools/ship_pro.py"
},
"evidence": "ue 필요 result = subprocess.run( command, cwd=str(project_path), shell=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/clouvel/tools/ship_pro.py",
"line": 242,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/clouvel/version_check.py)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/clouvel/version_check.py:37`): 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": "src/clouvel/version_check.py"
},
"evidence": "sts response = requests.get( \"https://pypi.org/pypi/clouvel/json\", timeout=5",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/clouvel/version_check.py",
"line": 37,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_explore\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_explore\" 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": "spawn_explore"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_librarian\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_librarian\" 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": "spawn_librarian"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"list_files\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"list_files\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "list_files",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"clouvel\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "clouvel"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"list_files"
],
"externalSink": [
"spawn_explore",
"spawn_librarian"
],
"selfContained": false,
"path": [
"list_files",
"spawn_explore"
],
"pathWired": true,
"description": "A sensitive-source → external-sink chain exists: list_files ⇒ spawn_explore."
}
],
"capabilities": [
{
"tool": "can_code",
"tags": [],
"reasons": {}
},
{
"tool": "scan_docs",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_docs",
"tags": [],
"reasons": {}
},
{
"tool": "init_docs",
"tags": [],
"reasons": {}
},
{
"tool": "get_prd_template",
"tags": [],
"reasons": {}
},
{
"tool": "list_templates",
"tags": [],
"reasons": {}
},
{
"tool": "write_prd_section",
"tags": [],
"reasons": {}
},
{
"tool": "get_prd_guide",
"tags": [],
"reasons": {}
},
{
"tool": "get_verify_checklist",
"tags": [],
"reasons": {}
},
{
"tool": "get_setup_guide",
"tags": [],
"reasons": {}
},
{
"tool": "get_analytics",
"tags": [],
"reasons": {}
},
{
"tool": "get_ab_report",
"tags": [],
"reasons": {}
},
{
"tool": "get_monthly_report",
"tags": [],
"reasons": {}
},
{
"tool": "decide_winner",
"tags": [],
"reasons": {}
},
{
"tool": "init_clouvel",
"tags": [],
"reasons": {}
},
{
"tool": "setup_cli",
"tags": [],
"reasons": {}
},
{
"tool": "init_rules",
"tags": [],
"reasons": {}
},
{
"tool": "get_rule",
"tags": [],
"reasons": {}
},
{
"tool": "audit_rules",
"tags": [],
"reasons": {}
},
{
"tool": "add_rule",
"tags": [],
"reasons": {}
},
{
"tool": "verify",
"tags": [],
"reasons": {}
},
{
"tool": "gate",
"tags": [],
"reasons": {}
},
{
"tool": "handoff",
"tags": [],
"reasons": {}
},
{
"tool": "init_planning",
"tags": [],
"reasons": {}
},
{
"tool": "plan",
"tags": [],
"reasons": {}
},
{
"tool": "save_finding",
"tags": [],
"reasons": {}
},
{
"tool": "refresh_goals",
"tags": [],
"reasons": {}
},
{
"tool": "update_progress",
"tags": [],
"reasons": {}
},
{
"tool": "context_save",
"tags": [],
"reasons": {}
},
{
"tool": "context_load",
"tags": [],
"reasons": {}
},
{
"tool": "spawn_explore",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "spawn_librarian",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "hook_design",
"tags": [],
"reasons": {}
},
{
"tool": "hook_verify",
"tags": [],
"reasons": {}
},
{
"tool": "start",
"tags": [],
"reasons": {}
},
{
"tool": "save_prd",
"tags": [],
"reasons": {}
},
{
"tool": "archive_project",
"tags": [],
"reasons": {}
},
{
"tool": "list_projects",
"tags": [],
"reasons": {}
},
{
"tool": "record_decision",
"tags": [],
"reasons": {}
},
{
"tool": "record_location",
"tags": [],
"reasons": {}
},
{
"tool": "search_knowledge",
"tags": [],
"reasons": {}
},
{
"tool": "get_context",
"tags": [],
"reasons": {}
},
{
"tool": "init_knowledge",
"tags": [],
"reasons": {}
},
{
"tool": "rebuild_index",
"tags": [],
"reasons": {}
},
{
"tool": "unlock_decision",
"tags": [],
"reasons": {}
},
{
"tool": "list_locked_decisions",
"tags": [],
"reasons": {}
},
{
"tool": "record_file",
"tags": [],
"reasons": {}
},
{
"tool": "list_files",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "manager",
"tags": [],
"reasons": {}
},
{
"tool": "list_managers",
"tags": [],
"reasons": {}
},
{
"tool": "quick_perspectives",
"tags": [],
"reasons": {}
},
{
"tool": "ship",
"tags": [],
"reasons": {}
},
{
"tool": "quick_ship",
"tags": [],
"reasons": {}
},
{
"tool": "full_ship",
"tags": [],
"reasons": {}
},
{
"tool": "error_record",
"tags": [],
"reasons": {}
},
{
"tool": "error_check",
"tags": [],
"reasons": {}
},
{
"tool": "error_learn",
"tags": [],
"reasons": {}
},
{
"tool": "memory_status",
"tags": [],
"reasons": {}
},
{
"tool": "memory_list",
"tags": [],
"reasons": {}
},
{
"tool": "memory_search",
"tags": [],
"reasons": {}
},
{
"tool": "memory_archive",
"tags": [],
"reasons": {}
},
{
"tool": "memory_report",
"tags": [],
"reasons": {}
},
{
"tool": "memory_promote",
"tags": [],
"reasons": {}
},
{
"tool": "memory_global_search",
"tags": [],
"reasons": {}
},
{
"tool": "set_project_domain",
"tags": [],
"reasons": {}
},
{
"tool": "activate_license",
"tags": [],
"reasons": {}
},
{
"tool": "license_status",
"tags": [],
"reasons": {}
},
{
"tool": "arch_check",
"tags": [],
"reasons": {}
},
{
"tool": "check_imports",
"tags": [],
"reasons": {}
},
{
"tool": "check_duplicates",
"tags": [],
"reasons": {}
},
{
"tool": "check_sync",
"tags": [],
"reasons": {}
},
{
"tool": "debug_runtime",
"tags": [],
"reasons": {}
},
{
"tool": "drift_check",
"tags": [],
"reasons": {}
},
{
"tool": "pattern_watch",
"tags": [],
"reasons": {}
},
{
"tool": "auto_remind",
"tags": [],
"reasons": {}
},
{
"tool": "meeting",
"tags": [],
"reasons": {}
},
{
"tool": "meeting_topics",
"tags": [],
"reasons": {}
},
{
"tool": "rate_meeting",
"tags": [],
"reasons": {}
},
{
"tool": "get_meeting_stats",
"tags": [],
"reasons": {}
},
{
"tool": "export_training_data",
"tags": [],
"reasons": {}
},
{
"tool": "enable_ab_testing",
"tags": [],
"reasons": {}
},
{
"tool": "disable_ab_testing",
"tags": [],
"reasons": {}
},
{
"tool": "get_variant_performance",
"tags": [],
"reasons": {}
},
{
"tool": "list_variants",
"tags": [],
"reasons": {}
},
{
"tool": "configure_meeting",
"tags": [],
"reasons": {}
},
{
"tool": "add_persona_override",
"tags": [],
"reasons": {}
},
{
"tool": "get_meeting_config",
"tags": [],
"reasons": {}
},
{
"tool": "reset_meeting_config",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "06c0c2ae9fa49c6e661da61af0f783280e6f09b5363fb1e75167742aff847bc3",
"stats": {
"tools": 88,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 1,
"low": 3,
"info": 1
}
}
}