World Model — the complete, unedited output of the deterministic mcptrustchecker engine v1.10.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.10.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "world-model-mcp",
"source": {
"kind": "package",
"origin": "world-model-mcp"
},
"server": {
"name": "world-model-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 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 (31 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-SRC-002",
"title": "Shell/command execution in server code (adapters/pi/index.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`adapters/pi/index.ts:22`): 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": "adapters/pi/index.ts"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { mkdirSync } from \"node:fs\"; import { homedir } from \"node:os\"; import {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "adapters/pi/index.ts",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (hooks/src/world-model-inject.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`hooks/src/world-model-inject.ts: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": "hooks/src/world-model-inject.ts"
},
"evidence": "import { spawn } from 'child_process'; type EventName = 'PostCompact' | 'UserPromptSubmit' | 'SessionStart'; interfac",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "hooks/src/world-model-inject.ts",
"line": 11,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/repeat-mistake/agent_runner.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/repeat-mistake/agent_runner.py:184`): 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": "benchmarks/repeat-mistake/agent_runner.py"
},
"evidence": "try: proc = subprocess.run( cmd, cwd=str(checkout.repo_dir),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/repeat-mistake/agent_runner.py",
"line": 184,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/repeat-mistake/claude_client.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/repeat-mistake/claude_client.py:86`): 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": "benchmarks/repeat-mistake/claude_client.py"
},
"evidence": "proc = subprocess.run( [self.binary, \"-p\", \"--output-format\", \"text\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/repeat-mistake/claude_client.py",
"line": 86,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/repeat-mistake/clone_repo.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/repeat-mistake/clone_repo.py:39`): 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": "benchmarks/repeat-mistake/clone_repo.py"
},
"evidence": "stderr).\"\"\" proc = subprocess.run( cmd, cwd=cwd, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/repeat-mistake/clone_repo.py",
"line": 39,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/repeat-mistake/score.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/repeat-mistake/score.py:56`): 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": "benchmarks/repeat-mistake/score.py"
},
"evidence": "join(cmd)}\") proc = subprocess.run(cmd, env=os.environ.copy()) return proc.returncode def collect_results(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/repeat-mistake/score.py",
"line": 56,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/managed-agents-self-hosted/deploy_modal.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/managed-agents-self-hosted/deploy_modal.py:54`): 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": "examples/managed-agents-self-hosted/deploy_modal.py"
},
"evidence": "Modal immediately. subprocess.Popen([\"python\", \"-m\", \"world_model_server.server\"])",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/managed-agents-self-hosted/deploy_modal.py",
"line": 54,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/engagement_tracker.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/engagement_tracker.py:78`): 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": "scripts/engagement_tracker.py"
},
"evidence": "d JSON.\"\"\" result = subprocess.run( [\"gh\", \"api\", path], capture_output=True, text=True, timeout=15,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/engagement_tracker.py",
"line": 78,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/integration/test_buzz_acp_handshake.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration/test_buzz_acp_handshake.py:195`): 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": "tests/integration/test_buzz_acp_handshake.py"
},
"evidence": "oot, }) proc = subprocess.Popen( [buzz_agent], stdin=subprocess.PIPE, stdout=subprocess",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/integration/test_buzz_acp_handshake.py",
"line": 195,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_etch_verify_subprocess_e2e.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_etch_verify_subprocess_e2e.py:80`): 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": "tests/test_etch_verify_subprocess_e2e.py"
},
"evidence": "nts. \"\"\" return subprocess.run( [sys.executable, \"-m\", \"world_model_server.etch_verify\", *args],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_etch_verify_subprocess_e2e.py",
"line": 80,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"world-model-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": "world-model-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "query_fact",
"tags": [],
"reasons": {}
},
{
"tool": "record_event",
"tags": [],
"reasons": {}
},
{
"tool": "validate_change",
"tags": [],
"reasons": {}
},
{
"tool": "get_constraints",
"tags": [],
"reasons": {}
},
{
"tool": "record_correction",
"tags": [],
"reasons": {}
},
{
"tool": "get_related_bugs",
"tags": [],
"reasons": {}
},
{
"tool": "seed_project",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_pr_reviews",
"tags": [],
"reasons": {}
},
{
"tool": "record_decision",
"tags": [],
"reasons": {}
},
{
"tool": "pin_annotation",
"tags": [],
"reasons": {}
},
{
"tool": "get_decision_log",
"tags": [],
"reasons": {}
},
{
"tool": "record_test_outcome",
"tags": [],
"reasons": {}
},
{
"tool": "get_co_edit_suggestions",
"tags": [],
"reasons": {}
},
{
"tool": "search_global",
"tags": [],
"reasons": {}
},
{
"tool": "predict_regression",
"tags": [],
"reasons": {}
},
{
"tool": "simulate_change",
"tags": [],
"reasons": {}
},
{
"tool": "predict_test_failures",
"tags": [],
"reasons": {}
},
{
"tool": "promote_constraint",
"tags": [],
"reasons": {}
},
{
"tool": "get_health_report",
"tags": [],
"reasons": {}
},
{
"tool": "get_context_for_action",
"tags": [],
"reasons": {}
},
{
"tool": "find_contradictions",
"tags": [],
"reasons": {}
},
{
"tool": "recall_transcript_range",
"tags": [],
"reasons": {}
},
{
"tool": "export_claude_md",
"tags": [],
"reasons": {}
},
{
"tool": "get_injection_context",
"tags": [],
"reasons": {}
},
{
"tool": "record_compaction_audit",
"tags": [],
"reasons": {}
},
{
"tool": "get_compaction_audit",
"tags": [],
"reasons": {}
},
{
"tool": "get_agents_md_constraints",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_contradiction",
"tags": [],
"reasons": {}
},
{
"tool": "verify_retrieval",
"tags": [],
"reasons": {}
},
{
"tool": "prove_entry_inclusion",
"tags": [],
"reasons": {}
},
{
"tool": "get_audit_log_head",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "78bfe6e59f66c2be8911af8e67bf3f3da3a7dc51c5cc295c7abba91f93e14c42",
"stats": {
"tools": 31,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 0,
"low": 8,
"info": 1
}
}
}