Iranti — 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": "iranti",
"source": {
"kind": "package",
"origin": "iranti"
},
"server": {
"name": "iranti"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (19 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 (dist/src/lib/commandInvocation.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/commandInvocation.js:29`): 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/src/lib/commandInvocation.js"
},
"evidence": "require(\"path\")); const child_process_1 = require(\"child_process\"); function windowsNodeToolScript(name) { const nod",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/lib/commandInvocation.js",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/lib/runtimeDependencies.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/runtimeDependencies.js:27`): 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/src/lib/runtimeDependencies.js"
},
"evidence": "(require(\"net\")); const child_process_1 = require(\"child_process\"); function runCommandCapture(executable, args, cwd) {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/lib/runtimeDependencies.js",
"line": 27,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/lib/runtimeLifecycle.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/runtimeLifecycle.js:52`): 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/src/lib/runtimeLifecycle.js"
},
"evidence": "require(\"path\")); const child_process_1 = require(\"child_process\"); const fileMutation_1 = require(\"./fileMutation\"); fu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/lib/runtimeLifecycle.js",
"line": 52,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/lib/test-copilot-bootstrap.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/test-copilot-bootstrap.js:13`): 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/src/lib/test-copilot-bootstrap.js"
},
"evidence": "_state in DB. */ const child_process_1 = require(\"child_process\"); const path_1 = __importDefault(require(\"path\")); con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/lib/test-copilot-bootstrap.js",
"line": 13,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/src/lib/providers/gemini.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/providers/gemini.js:26`): 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": "dist/src/lib/providers/gemini.js"
},
"evidence": "const response = await fetch(`https://generativelanguage.googleapis.com/v1beta/models/${model}:generateContent?key=${th",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/src/lib/providers/gemini.js",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/src/lib/providers/groq.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/providers/groq.js:26`): 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": "dist/src/lib/providers/groq.js"
},
"evidence": "const response = await fetch('https://api.groq.com/openai/v1/chat/completions', { method: 'POST',",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/src/lib/providers/groq.js",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/src/lib/providers/mistral.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/lib/providers/mistral.js:26`): 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": "dist/src/lib/providers/mistral.js"
},
"evidence": "const response = await fetch('https://api.mistral.ai/v1/chat/completions', { method: 'POST', he",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/src/lib/providers/mistral.js",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (bin/iranti-mcp-server.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`bin/iranti-mcp-server.js:22`): 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": "bin/iranti-mcp-server.js"
},
"evidence": "xistsSync(distMcp)) { require(distMcp); return; } try { require('ts-node/register/transpile-only'); require(src",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "bin/iranti-mcp-server.js",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (bin/iranti.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`bin/iranti.js:12`): 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": "bin/iranti.js"
},
"evidence": "xistsSync(distCli)) { require(distCli); return; } try { require('ts-node/register/transpile-only'); require(src",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "bin/iranti.js",
"line": 12,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/scripts/iranti-cli.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/iranti-cli.js:31`): 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/scripts/iranti-cli.js"
},
"evidence": "require(\"path\")); const child_process_1 = require(\"child_process\"); const https_1 = __importDefault(require(\"https\")); c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/scripts/iranti-cli.js",
"line": 31,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/scripts/setup.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/setup.js:15`): 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/scripts/setup.js"
},
"evidence": "\"dotenv/config\"); const child_process_1 = require(\"child_process\"); const fs_1 = __importDefault(require(\"fs\")); const p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/scripts/setup.js",
"line": 15,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal in packaging/dev tooling (dist/scripts/iranti-cli.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/iranti-cli.js:1059`): 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/scripts/iranti-cli.js"
},
"evidence": "int/no-var-requires require(serverEntry); } async function stopRuntimeProcess(pid, timeoutMs) { if (!(0, runtime",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/scripts/iranti-cli.js",
"line": 1059,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "iranti_handshake",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_attend",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"search web\""
]
}
},
{
"tool": "iranti_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_observe",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_query",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_history",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_search",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_write",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_write_rule",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_write_issue",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_remember_response",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_ingest",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_relate",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_related",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_related_deep",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_who_knows",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_remember",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_recall",
"tags": [],
"reasons": {}
},
{
"tool": "iranti_forget",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b90209a2a37bfab240be7b3120201cd3df466b26098e29c70c81edab630b7a52",
"stats": {
"tools": 19,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 5,
"low": 3,
"info": 0
}
}
}