Scrub — 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": "scrub-mcp",
"source": {
"kind": "package",
"origin": "scrub-mcp"
},
"server": {
"name": "scrub-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": [
"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 (22 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 (src/scrub_mcp/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/cli.py:599`): 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/scrub_mcp/cli.py"
},
"evidence": "try: subprocess.run([\"git\", \"checkout\", \"-b\", branch], check=True) if not quiet:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/cli.py",
"line": 599,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/mcp/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/mcp/server.py:1049`): 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/scrub_mcp/mcp/server.py"
},
"evidence": "proc = subprocess.run(rg_cmd, capture_output=True, text=True, timeout=15) for line",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/mcp/server.py",
"line": 1049,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/tools/diff.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/tools/diff.py:113`): 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/scrub_mcp/tools/diff.py"
},
"evidence": ". \"\"\" result = subprocess.run( [\"git\", \"diff\", \"-M\", since], cwd=repo_path, capture_out",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/tools/diff.py",
"line": 113,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/tools/imports.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/tools/imports.py:97`): 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/scrub_mcp/tools/imports.py"
},
"evidence": "rt (I) result = subprocess.run( [ \"ruff\", \"check\", \"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/tools/imports.py",
"line": 97,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/tools/linter.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/tools/linter.py:37`): 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/scrub_mcp/tools/linter.py"
},
"evidence": "check_result = subprocess.run( [\"ruff\", \"check\", \"--output-format\", \"json\"] + common_flags + [str(t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/tools/linter.py",
"line": 37,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/tools/sbom.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/tools/sbom.py:42`): 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/scrub_mcp/tools/sbom.py"
},
"evidence": "try: result = subprocess.run( [sys.executable, \"-m\", \"pip\", \"freeze\", \"--all\"], captur",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/tools/sbom.py",
"line": 42,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/tools/security.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/tools/security.py:63`): 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/scrub_mcp/tools/security.py"
},
"evidence": "ath)) result = subprocess.run( cmd, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/tools/security.py",
"line": 63,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scrub_mcp/utils.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scrub_mcp/utils.py:89`): 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/scrub_mcp/utils.py"
},
"evidence": "name) result = subprocess.run( [ \"pydocstyle\", \"--convention=google",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scrub_mcp/utils.py",
"line": 89,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"scrub-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": "scrub-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "lint_file",
"tags": [],
"reasons": {}
},
{
"tool": "generate_docstrings",
"tags": [],
"reasons": {}
},
{
"tool": "annotate_types",
"tags": [],
"reasons": {}
},
{
"tool": "add_comments",
"tags": [],
"reasons": {}
},
{
"tool": "hygiene_full",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_complexity",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_simplifications",
"tags": [],
"reasons": {}
},
{
"tool": "optimize_imports",
"tags": [],
"reasons": {}
},
{
"tool": "generate_tests",
"tags": [],
"reasons": {}
},
{
"tool": "find_dead_code",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_refactoring",
"tags": [],
"reasons": {}
},
{
"tool": "run_tests",
"tags": [],
"reasons": {}
},
{
"tool": "security_scan",
"tags": [],
"reasons": {}
},
{
"tool": "security_remediate",
"tags": [],
"reasons": {}
},
{
"tool": "generate_sbom",
"tags": [],
"reasons": {}
},
{
"tool": "scan_vulnerabilities",
"tags": [],
"reasons": {}
},
{
"tool": "read_files",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "find_symbols",
"tags": [],
"reasons": {}
},
{
"tool": "grep_multi",
"tags": [],
"reasons": {}
},
{
"tool": "explore_architecture",
"tags": [],
"reasons": {}
},
{
"tool": "hygiene_batch",
"tags": [],
"reasons": {}
},
{
"tool": "hygiene_incremental",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e9c671e82f062e012f3b99396887873e199e6c9c45f71184b75d2bfca9c4c925",
"stats": {
"tools": 22,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 0,
"info": 1
}
}
}