Batch Review — 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": "batch-review-mcp",
"source": {
"kind": "package",
"origin": "batch-review-mcp"
},
"server": {
"name": "batch-review-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": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (20 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-001",
"title": "Dynamic code execution in server code (frontend/dist/assets/index-BsHH-Oq2.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`frontend/dist/assets/index-BsHH-Oq2.js:653`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "frontend/dist/assets/index-BsHH-Oq2.js"
},
"evidence": "==\"textarea\")try{source=eval(\"(\"+TheTextBox.value+\")\")}catch(xe){return erra(xe)}else try{source=eval(\"(\"+TheTextBox.inn",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "frontend/dist/assets/index-BsHH-Oq2.js",
"line": 653,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (backend/cli_client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`backend/cli_client.py:288`): 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": "backend/cli_client.py"
},
"evidence": "try: proc = subprocess.Popen( # noqa: S603 — cmd is constructed internally cmd, std",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "backend/cli_client.py",
"line": 288,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (frontend/dist/assets/PdfViewer-62czSgTP.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`frontend/dist/assets/PdfViewer-62czSgTP.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": "frontend/dist/assets/PdfViewer-62czSgTP.js"
},
"evidence": "(a.split(\"+\").at(-1)))}}exec(t,e){if(!this.allKeys.has(e.key))return;const s=this.callbacks.get(g(this,ih,mu).call(this,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "frontend/dist/assets/PdfViewer-62czSgTP.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (main.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`main.py:66`): 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": "main.py"
},
"evidence": "ci)…\") result = subprocess.run( npm + [\"ci\"], cwd=str(_FRONTEND_DIR), check=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "main.py",
"line": 66,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (frontend/dist/assets/PdfViewer-62czSgTP.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`frontend/dist/assets/PdfViewer-62czSgTP.js:2`): 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": "frontend/dist/assets/PdfViewer-62czSgTP.js"
},
"evidence": "l)?r(this,Ur,Ml):(await import(this.workerSrc)).WorkerMessageHandler)())}};fh=new WeakMap,Sn=new WeakMap,xn=new WeakMap,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "frontend/dist/assets/PdfViewer-62czSgTP.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/build_mcpb.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/build_mcpb.py:30`): 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/build_mcpb.py"
},
"evidence": "--\", \"mcpb\", *args] subprocess.run(cmd, cwd=str(cwd), check=True) def _read_project_version(pyproject: Path) -> st",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/build_mcpb.py",
"line": 30,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/capture_screenshot.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/capture_screenshot.py:156`): 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/capture_screenshot.py"
},
"evidence": ") server_proc = subprocess.Popen( [sys.executable, str(REPO_ROOT / \"main.py\"), \"--root\", str(args.ro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/capture_screenshot.py",
"line": 156,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/session_history_metadata.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/session_history_metadata.py:85`): 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/session_history_metadata.py"
},
"evidence": "ys.stderr) result = subprocess.run( [agent_cmd, \"about\", \"--format\", \"json\"], check=True, ca",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/session_history_metadata.py",
"line": 85,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"batch-review-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "batch-review-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "init_batch_review_session",
"tags": [],
"reasons": {}
},
{
"tool": "list_directory",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "get_file_content",
"tags": [],
"reasons": {}
},
{
"tool": "get_git_changes",
"tags": [],
"reasons": {}
},
{
"tool": "get_git_diff",
"tags": [],
"reasons": {}
},
{
"tool": "open_file_in_ui",
"tags": [],
"reasons": {}
},
{
"tool": "highlight_in_ui",
"tags": [],
"reasons": {}
},
{
"tool": "jump_to_comment_in_ui",
"tags": [],
"reasons": {}
},
{
"tool": "add_comment",
"tags": [],
"reasons": {}
},
{
"tool": "list_comments",
"tags": [],
"reasons": {}
},
{
"tool": "recompute_comment_stale",
"tags": [],
"reasons": {}
},
{
"tool": "delete_comment",
"tags": [],
"reasons": {}
},
{
"tool": "clear_all_comments",
"tags": [],
"reasons": {}
},
{
"tool": "delete_outdated_comments",
"tags": [],
"reasons": {}
},
{
"tool": "update_comment",
"tags": [],
"reasons": {}
},
{
"tool": "save_comments",
"tags": [],
"reasons": {}
},
{
"tool": "get_config",
"tags": [],
"reasons": {}
},
{
"tool": "get_review_web_url",
"tags": [],
"reasons": {}
},
{
"tool": "list_review_files",
"tags": [],
"reasons": {}
},
{
"tool": "load_review_by_stem",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "dd18b38bffad25a6c809d137ffd55bc906b7bb6da1c304767268b03fd8794481",
"stats": {
"tools": 20,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 1,
"low": 3,
"info": 1
}
}
}