Token Optimizer — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "token-optimizer-mcp",
"source": {
"kind": "package",
"origin": "token-optimizer-mcp"
},
"server": {
"name": "token-optimizer-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-1.8"
},
"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 (11 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-CAP-001",
"title": "Tool \"get_session_stats\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"get_session_stats\" appears to run shell commands or evaluate code (keyword \"powershell\"). 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": "get_session_stats"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/tools/code-analysis/smart-security.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/code-analysis/smart-security.js:149`): 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": "dist/tools/code-analysis/smart-security.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/tools/code-analysis/smart-security.js",
"line": 149
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cli-wrapper.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cli-wrapper.mjs:17`): 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": "cli-wrapper.mjs"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cli-wrapper.mjs",
"line": 17
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-build.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-build.js:10`): 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": "dist/tools/build-systems/smart-build.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-build.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-docker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-docker.js:10`): 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": "dist/tools/build-systems/smart-docker.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-docker.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-install.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-install.js:10`): 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": "dist/tools/build-systems/smart-install.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-install.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-lint.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-lint.js:10`): 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": "dist/tools/build-systems/smart-lint.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-lint.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-logs.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-logs.js:10`): 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": "dist/tools/build-systems/smart-logs.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-logs.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-network.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-network.js: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": "dist/tools/build-systems/smart-network.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-network.js",
"line": 11
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-processes.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-processes.js:10`): 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": "dist/tools/build-systems/smart-processes.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-processes.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-system-metrics.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-system-metrics.js:10`): 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": "dist/tools/build-systems/smart-system-metrics.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-system-metrics.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/build-systems/smart-test.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/build-systems/smart-test.js:10`): 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": "dist/tools/build-systems/smart-test.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/build-systems/smart-test.js",
"line": 10
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/tools/advanced-caching/smart-cache.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/tools/advanced-caching/smart-cache.js:132`): 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": "dist/tools/advanced-caching/smart-cache.js"
},
"evidence": "import(options)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/tools/advanced-caching/smart-cache.js",
"line": 132
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/tools/code-analysis/smart-imports.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/tools/code-analysis/smart-imports.js:391`): 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": "dist/tools/code-analysis/smart-imports.js"
},
"evidence": "import(s)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/tools/code-analysis/smart-imports.js",
"line": 391
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"get_session_stats\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"get_session_stats\" 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": "get_session_stats"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "optimize_text",
"tags": [],
"reasons": {}
},
{
"tool": "get_cached",
"tags": [],
"reasons": {}
},
{
"tool": "count_tokens",
"tags": [],
"reasons": {}
},
{
"tool": "compress_text",
"tags": [],
"reasons": {}
},
{
"tool": "decompress_text",
"tags": [],
"reasons": {}
},
{
"tool": "get_cache_stats",
"tags": [],
"reasons": {}
},
{
"tool": "clear_cache",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_optimization",
"tags": [],
"reasons": {}
},
{
"tool": "get_session_stats",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"powershell\""
]
}
},
{
"tool": "optimize_session",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_project_tokens",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "740e420d546113534a98eac39c430653b0ac12a2fc5ec845e5caba69b4634e07",
"stats": {
"tools": 11,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 12,
"medium": 2,
"low": 1,
"info": 0
}
}
}