Defense — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "defense-mcp-server",
"source": {
"kind": "package",
"origin": "defense-mcp-server"
},
"server": {
"name": "defense-mcp-server"
}
},
"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-1.13"
},
"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 (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-006",
"title": "Reads a sensitive credential path or dumps the environment (build/tools/cloud-security.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/tools/cloud-security.js:28`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "build/tools/cloud-security.js"
},
"evidence": "rovider: \"aws\", path: \"~/.aws/credentials\" }, { provider: \"aws\", path: \"~/.aws/config\" }, { provider: \"gcp\", pat",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "build/tools/cloud-security.js",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (build/tools/deception.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/tools/deception.js:109`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "build/tools/deception.js"
},
"evidence": "{ name: \"id_rsa\", content: generateFakeSshKey(), }, { name: \".env",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "build/tools/deception.js",
"line": 109,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (build/tools/process-security.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/tools/process-security.js:481`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "build/tools/process-security.js"
},
"evidence": "\", \"/etc/passwd\", \".ssh/id_rsa\", \".ssh/id_ed25519\", \"private.key\"]; const checkProcs = processList.slice(0, 20); //",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "build/tools/process-security.js",
"line": 481,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (build/tools/secrets.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/tools/secrets.js:103`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "build/tools/secrets.js"
},
"evidence": "\"-o\", \"-name\", \"id_rsa\", \"-o\", \"-name\", \"id_ecdsa\",",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "build/tools/secrets.js",
"line": 103,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/core/command-allowlist.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/core/command-allowlist.js:26`): 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": "build/core/command-allowlist.js"
},
"evidence": ", execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; const execFileAsync = promisify(execFile)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/core/command-allowlist.js",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/core/executor.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/core/executor.js:1`): 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": "build/core/executor.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { existsSync } from \"node:fs\"; import { homedir } from \"node:os\"; import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/core/executor.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/core/spawn-safe.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/core/spawn-safe.js:16`): 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": "build/core/spawn-safe.js"
},
"evidence": "cFileSync, } from \"node:child_process\"; import { resolveCommand } from \"./command-allowlist.js\"; // ── Argument Redactio",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/core/spawn-safe.js",
"line": 16,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "access_control",
"tags": [],
"reasons": {}
},
{
"tool": "api_security",
"tags": [],
"reasons": {}
},
{
"tool": "app_harden",
"tags": [],
"reasons": {}
},
{
"tool": "backup",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_security",
"tags": [],
"reasons": {}
},
{
"tool": "compliance",
"tags": [],
"reasons": {}
},
{
"tool": "container_docker",
"tags": [],
"reasons": {}
},
{
"tool": "container_isolation",
"tags": [],
"reasons": {}
},
{
"tool": "honeypot_manage",
"tags": [],
"reasons": {}
},
{
"tool": "dns_security",
"tags": [],
"reasons": {}
},
{
"tool": "ebpf",
"tags": [],
"reasons": {}
},
{
"tool": "crypto",
"tags": [],
"reasons": {}
},
{
"tool": "firewall",
"tags": [],
"reasons": {}
},
{
"tool": "harden_kernel",
"tags": [],
"reasons": {}
},
{
"tool": "harden_host",
"tags": [],
"reasons": {}
},
{
"tool": "incident_response",
"tags": [],
"reasons": {}
},
{
"tool": "integrity",
"tags": [],
"reasons": {}
},
{
"tool": "log_management",
"tags": [],
"reasons": {}
},
{
"tool": "malware",
"tags": [],
"reasons": {}
},
{
"tool": "defense_mgmt",
"tags": [],
"reasons": {}
},
{
"tool": "network_defense",
"tags": [],
"reasons": {}
},
{
"tool": "patch",
"tags": [],
"reasons": {}
},
{
"tool": "process_security",
"tags": [],
"reasons": {}
},
{
"tool": "secrets",
"tags": [],
"reasons": {}
},
{
"tool": "sudo_session",
"tags": [],
"reasons": {}
},
{
"tool": "supply_chain",
"tags": [],
"reasons": {}
},
{
"tool": "threat_intel",
"tags": [],
"reasons": {}
},
{
"tool": "vuln_manage",
"tags": [],
"reasons": {}
},
{
"tool": "waf_manage",
"tags": [],
"reasons": {}
},
{
"tool": "wireless_security",
"tags": [],
"reasons": {}
},
{
"tool": "zero_trust",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "ea4d80d051ae9f25e99684313aca0a0ca3e1c3d4c2252bfe9ade60a8a45f0cd1",
"stats": {
"tools": 31,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 0,
"low": 0,
"info": 0
}
}
}