Agent Security — 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": "mcp-server-agent-security",
"source": {
"kind": "package",
"origin": "mcp-server-agent-security"
},
"server": {
"name": "mcp-server-agent-security"
}
},
"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 send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"sensitive-source",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (9 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 (lib/package-scanner.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/package-scanner.js:384`): 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": "lib/package-scanner.js"
},
"evidence": "(/(^|\\/)(\\.env|\\.npmrc|id_rsa|id_dsa|.*\\.pem|.*\\.key)$/i.test(relativePath)) { permissionAnalysis.sensitivePackag",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "lib/package-scanner.js",
"line": 384,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"audit_mcp_server\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"audit_mcp_server\" appears to run shell commands or evaluate code (parameter \"command\"). 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": "audit_mcp_server"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (lib/package-scanner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/package-scanner.js:45`): 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": "lib/package-scanner.js"
},
"evidence": "cription: \"Package uses eval().\", remediation: \"Remove dynamic evaluation or replace it with safe parsing and fixed",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "lib/package-scanner.js",
"line": 45,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/package-scanner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/package-scanner.js:4`): 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": "lib/package-scanner.js"
},
"evidence": "{ execFile } = require(\"child_process\"); const { promisify } = require(\"util\"); const { createFinding, dedupeFindings }",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/package-scanner.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (cli.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`cli.js:47`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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.js"
},
"evidence": "const response = await fetch(`http://${HOST}:${PORT}${pathname}`, { method, headers, body: payload ? JSON.s",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "cli.js",
"line": 47,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"audit_mcp_server\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"audit_mcp_server\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "audit_mcp_server",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (lib/utils.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`lib/utils.js:29`): 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": "lib/utils.js"
},
"evidence": "ry { return await import(specifier); } catch (error) { lastError = error; } } throw lastError;",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "lib/utils.js",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"audit_mcp_server\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"audit_mcp_server\" 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": "audit_mcp_server"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "audit_mcp_config",
"tags": [],
"reasons": {}
},
{
"tool": "audit_mcp_server",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "audit_prompt_injection",
"tags": [],
"reasons": {}
},
{
"tool": "audit_agent_dataflow",
"tags": [],
"reasons": {}
},
{
"tool": "scan_mcp_package",
"tags": [],
"reasons": {}
},
{
"tool": "generate_report",
"tags": [],
"reasons": {}
},
{
"tool": "fix_mcp_config",
"tags": [],
"reasons": {}
},
{
"tool": "harden_system_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "generate_policy",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d0fca7bd80a6175c08a0bc89a8183150c1a83540830468f3607dc032bc4866db",
"stats": {
"tools": 9,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 3,
"low": 1,
"info": 0
}
}
}