Vectros Ai — 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": "@vectros-ai/mcp-server",
"source": {
"kind": "package",
"origin": "@vectros-ai/mcp-server"
},
"server": {
"name": "@vectros-ai/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": [
"ingests untrusted external content (a prompt-injection entry point)",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"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 (24 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 (dist/cli-http.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli-http.js:10871`): 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": "dist/cli-http.js"
},
"evidence": "v\", \"credentials\", \"id_rsa\", \"id_ed25519\", \"id_ecdsa\", \"id_dsa\", \".npmrc\", \".netrc\", \".pgpass\" ]); async",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/cli-http.js",
"line": 10871,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/cli-http.mjs)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli-http.mjs:10853`): 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": "dist/cli-http.mjs"
},
"evidence": "v\", \"credentials\", \"id_rsa\", \"id_ed25519\", \"id_ecdsa\", \"id_dsa\", \".npmrc\", \".netrc\", \".pgpass\" ]); async",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/cli-http.mjs",
"line": 10853,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/cli.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.js:10874`): 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": "dist/cli.js"
},
"evidence": "v\", \"credentials\", \"id_rsa\", \"id_ed25519\", \"id_ecdsa\", \"id_dsa\", \".npmrc\", \".netrc\", \".pgpass\" ]); async",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/cli.js",
"line": 10874,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/cli.mjs)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.mjs:10856`): 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": "dist/cli.mjs"
},
"evidence": "v\", \"credentials\", \"id_rsa\", \"id_ed25519\", \"id_ecdsa\", \"id_dsa\", \".npmrc\", \".netrc\", \".pgpass\" ]); async",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/cli.mjs",
"line": 10856,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/index.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:10887`): 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": "dist/index.js"
},
"evidence": "v\", \"credentials\", \"id_rsa\", \"id_ed25519\", \"id_ecdsa\", \"id_dsa\", \".npmrc\", \".netrc\", \".pgpass\" ]); async",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/index.js",
"line": 10887,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/index.mjs)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.mjs:10851`): 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": "dist/index.mjs"
},
"evidence": "v\", \"credentials\", \"id_rsa\", \"id_ed25519\", \"id_ecdsa\", \"id_dsa\", \".npmrc\", \".netrc\", \".pgpass\" ]); async",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/index.mjs",
"line": 10851,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli-http.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli-http.js:11796`): 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/cli-http.js"
},
"evidence": "-key.ts var import_node_child_process = require(\"child_process\"); var import_node_fs = require(\"fs\"); var import_node_pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli-http.js",
"line": 11796,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli-http.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli-http.mjs:11778`): 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/cli-http.mjs"
},
"evidence": "port { execFile } from \"child_process\"; import { statSync } from \"fs\"; import path from \"path\"; var HELPER_COMMAND = \"ve",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli-http.mjs",
"line": 11778,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.js:11663`): 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/cli.js"
},
"evidence": "-key.ts var import_node_child_process = require(\"child_process\"); var import_node_fs = require(\"fs\"); var import_node_pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli.js",
"line": 11663,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.mjs:11645`): 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/cli.mjs"
},
"evidence": "port { execFile } from \"child_process\"; import { statSync } from \"fs\"; import path from \"path\"; var HELPER_COMMAND = \"ve",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli.mjs",
"line": 11645,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "hybrid_search",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "record_query",
"tags": [],
"reasons": {}
},
{
"tool": "record_get",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "record_batch_get",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "record_create",
"tags": [],
"reasons": {}
},
{
"tool": "record_update",
"tags": [],
"reasons": {}
},
{
"tool": "record_delete",
"tags": [],
"reasons": {}
},
{
"tool": "rag_ask",
"tags": [],
"reasons": {}
},
{
"tool": "document_ask",
"tags": [],
"reasons": {}
},
{
"tool": "list_schemas",
"tags": [],
"reasons": {}
},
{
"tool": "document_get",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "document_query",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "document_update",
"tags": [],
"reasons": {}
},
{
"tool": "document_delete",
"tags": [],
"reasons": {}
},
{
"tool": "folder_query",
"tags": [],
"reasons": {}
},
{
"tool": "folder_create",
"tags": [],
"reasons": {}
},
{
"tool": "folder_update",
"tags": [],
"reasons": {}
},
{
"tool": "folder_delete",
"tags": [],
"reasons": {}
},
{
"tool": "current_identity",
"tags": [],
"reasons": {}
},
{
"tool": "document_ingest",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "lookup_principal",
"tags": [],
"reasons": {}
},
{
"tool": "version_history",
"tags": [],
"reasons": {}
},
{
"tool": "schemas",
"tags": [],
"reasons": {}
},
{
"tool": "identity",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "629cd8f2d315984535a532d0c3c9252313997e0cc0e604674363d752e05e1e6c",
"stats": {
"tools": 24,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 0,
"low": 0,
"info": 0
}
}
}