Teammcp — 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": "teammcp",
"source": {
"kind": "package",
"origin": "teammcp"
},
"server": {
"name": "teammcp"
}
},
"grade": "C",
"score": {
"score": 78,
"threatScore": 89,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 9.45,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 1.2,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"kind": "threat",
"ruleId": "MTC-SUP-010",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"tags": [
"external-sink",
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (45 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 (bin/teammcp.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/teammcp.mjs:12`): 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": "bin/teammcp.mjs"
},
"evidence": "rt { spawn } from 'node:child_process'; import { readFileSync } from 'node:fs'; import { join, dirname } from 'node:path",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/teammcp.mjs",
"line": 12,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (server/process-manager-mac.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`server/process-manager-mac.mjs:7`): 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": "server/process-manager-mac.mjs"
},
"evidence": "pawn, exec } from 'node:child_process'; import { existsSync, mkdirSync, writeFileSync, readFileSync, unlinkSync, copyFi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "server/process-manager-mac.mjs",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (server/process-manager-win.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`server/process-manager-win.mjs:6`): 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": "server/process-manager-win.mjs"
},
"evidence": ", execSync } from 'node:child_process'; import { existsSync, mkdirSync, writeFileSync, readFileSync, unlinkSync, copyFi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "server/process-manager-win.mjs",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (server/process-manager.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`server/process-manager.mjs:6`): 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": "server/process-manager.mjs"
},
"evidence": ", execSync } from 'node:child_process'; import { existsSync, mkdirSync, writeFileSync, readFileSync, unlinkSync, copyFi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "server/process-manager.mjs",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([download_file]) co-exist with external-action tools ([send_message, send_dm, upload_file]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "download_file → send_message"
},
"evidence": "untrusted [download_file] → sinks [send_message, send_dm, upload_file]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"download_file"
],
"sinks": [
"send_message",
"send_dm",
"upload_file"
]
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (server/process-manager-win.mjs)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`server/process-manager-win.mjs:38`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "server/process-manager-win.mjs"
},
"evidence": "olve, reject) => { exec(`powershell -NoProfile -Command \"${command}\"`, { shell: 'cmd.exe' }, (err, stdout, stderr)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "server/process-manager-win.mjs",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (server/process-manager.mjs)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`server/process-manager.mjs:38`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "server/process-manager.mjs"
},
"evidence": "olve, reject) => { exec(`powershell -NoProfile -Command \"${command}\"`, { shell: 'cmd.exe' }, (err, stdout, stderr)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "server/process-manager.mjs",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-010",
"title": "Package runs install-time scripts (postinstall)",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"description": "\"teammcp\" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.",
"remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
"location": {
"kind": "package",
"name": "teammcp"
},
"evidence": "node scripts/postinstall.mjs",
"owasp": "LLM03:2025 Supply Chain",
"references": [
"https://github.com/ossf/package-analysis",
"https://owasp.org/www-project-top-10-ci-cd-security-risks/"
],
"data": {
"scripts": [
"postinstall"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"download_file"
],
"sensitiveSource": [],
"externalSink": [
"send_message",
"send_dm",
"upload_file"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "send_dm",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"parameter \"recipient\""
]
}
},
{
"tool": "get_history",
"tags": [],
"reasons": {}
},
{
"tool": "get_agents",
"tags": [],
"reasons": {}
},
{
"tool": "get_channels",
"tags": [],
"reasons": {}
},
{
"tool": "create_channel",
"tags": [],
"reasons": {}
},
{
"tool": "edit_message",
"tags": [],
"reasons": {}
},
{
"tool": "delete_message",
"tags": [],
"reasons": {}
},
{
"tool": "search_messages",
"tags": [],
"reasons": {}
},
{
"tool": "start_agent",
"tags": [],
"reasons": {}
},
{
"tool": "stop_agent",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot_agent",
"tags": [],
"reasons": {}
},
{
"tool": "send_keys_to_agent",
"tags": [],
"reasons": {}
},
{
"tool": "pin_task",
"tags": [],
"reasons": {}
},
{
"tool": "create_task",
"tags": [],
"reasons": {}
},
{
"tool": "list_tasks",
"tags": [],
"reasons": {}
},
{
"tool": "update_task",
"tags": [],
"reasons": {}
},
{
"tool": "done_task",
"tags": [],
"reasons": {}
},
{
"tool": "check_knowledge_gaps",
"tags": [],
"reasons": {}
},
{
"tool": "acknowledge_knowledge_gaps",
"tags": [],
"reasons": {}
},
{
"tool": "get_agent_profile",
"tags": [],
"reasons": {}
},
{
"tool": "update_agent_profile",
"tags": [],
"reasons": {}
},
{
"tool": "get_inbox",
"tags": [],
"reasons": {}
},
{
"tool": "ack_inbox",
"tags": [],
"reasons": {}
},
{
"tool": "schedule_message",
"tags": [],
"reasons": {}
},
{
"tool": "list_schedules",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_schedule",
"tags": [],
"reasons": {}
},
{
"tool": "request_approval",
"tags": [],
"reasons": {}
},
{
"tool": "get_pending_approvals",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_approval",
"tags": [],
"reasons": {}
},
{
"tool": "get_changelog",
"tags": [],
"reasons": {}
},
{
"tool": "generate_audit_report",
"tags": [],
"reasons": {}
},
{
"tool": "get_audit_reports",
"tags": [],
"reasons": {}
},
{
"tool": "get_public_reports",
"tags": [],
"reasons": {}
},
{
"tool": "get_state",
"tags": [],
"reasons": {}
},
{
"tool": "set_state",
"tags": [],
"reasons": {}
},
{
"tool": "get_state_history",
"tags": [],
"reasons": {}
},
{
"tool": "subscribe_state",
"tags": [],
"reasons": {}
},
{
"tool": "add_reaction",
"tags": [],
"reasons": {}
},
{
"tool": "remove_reaction",
"tags": [],
"reasons": {}
},
{
"tool": "pin_message",
"tags": [],
"reasons": {}
},
{
"tool": "unpin_message",
"tags": [],
"reasons": {}
},
{
"tool": "get_pinned_messages",
"tags": [],
"reasons": {}
},
{
"tool": "upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "download_file",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
}
],
"surfaceDigest": "faf3ec046eb5e7c21dd733b95230379c43e982e215e1996b28995dc398838163",
"stats": {
"tools": 45,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 3,
"low": 1,
"info": 0
}
}
}