Talkito — 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": "talkito",
"source": {
"kind": "package",
"origin": "talkito"
},
"server": {
"name": "talkito"
}
},
"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": [
"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": [
"external-sink",
"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 (35 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 (talkito/asr.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/asr.py:1977`): 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": "talkito/asr.py"
},
"evidence": "credentials (env vars, ~/.aws/credentials, or IAM role)\" try: import boto3 # Try to create a session",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "talkito/asr.py",
"line": 1977,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (talkito/tts.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/tts.py:1087`): 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": "talkito/tts.py"
},
"evidence": "credentials (env vars, ~/.aws/credentials, or IAM role)\" try: import boto3 # Try to create a session",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "talkito/tts.py",
"line": 1087,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (setup.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`setup.py:32`): 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": "setup.py"
},
"evidence": "=\"utf-8\") as f: exec(compile(f.read(), version_file, \"exec\"), version_locals) return version_locals[\"__versi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "setup.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (setup.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`setup.py:32`): 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": "setup.py"
},
"evidence": "=\"utf-8\") as f: exec(compile(f.read(), version_file, \"exec\"), version_locals) return version_locals[\"__versi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "setup.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (talkito/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/cli.py:488`): 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": "talkito/cli.py"
},
"evidence": "try: subprocess.run(['pbcopy'], input=SLACK_BOT_MANIFEST.encode(), check=True) print(\"✅ M",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "talkito/cli.py",
"line": 488,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (talkito/clients.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/clients.py:190`): 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": "talkito/clients.py"
},
"evidence": "try: result = subprocess.run(['which', 'talkito'], capture_output=True, text=True) if result.returncod",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "talkito/clients.py",
"line": 190,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (talkito/comms.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/comms.py:1095`): 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": "talkito/comms.py"
},
"evidence": "self.tunnel_process = subprocess.Popen( zrok_cmd, stdin=subprocess.DEVNULL, # Prevent",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "talkito/comms.py",
"line": 1095,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (talkito/models.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/models.py:101`): 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": "talkito/models.py"
},
"evidence": "\") result = subprocess.run([ sys.executable, '-m', 'spacy', 'download', spacy_model",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "talkito/models.py",
"line": 101,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (talkito/tts.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/tts.py:818`): 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": "talkito/tts.py"
},
"evidence": "self.process = subprocess.Popen( chosen_cmd, stdout=subprocess.DEVNULL,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "talkito/tts.py",
"line": 818,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (talkito/update.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`talkito/update.py:139`): 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": "talkito/update.py"
},
"evidence": "cal changes subprocess.run(['git', 'stash'], capture_output=True) # Pull latest cha",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "talkito/update.py",
"line": 139,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "start_notification_stream",
"tags": [],
"reasons": {}
},
{
"tool": "get_talkito_status",
"tags": [],
"reasons": {}
},
{
"tool": "turn_on",
"tags": [],
"reasons": {}
},
{
"tool": "turn_off",
"tags": [],
"reasons": {}
},
{
"tool": "enable_tts",
"tags": [],
"reasons": {}
},
{
"tool": "disable_tts",
"tags": [],
"reasons": {}
},
{
"tool": "speak_text",
"tags": [],
"reasons": {}
},
{
"tool": "skip_current_speech",
"tags": [],
"reasons": {}
},
{
"tool": "stop_all_speech",
"tags": [],
"reasons": {}
},
{
"tool": "get_speech_status",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for_speech_completion",
"tags": [],
"reasons": {}
},
{
"tool": "change_tts",
"tags": [],
"reasons": {}
},
{
"tool": "configure_tts",
"tags": [],
"reasons": {}
},
{
"tool": "list_tts_voices",
"tags": [],
"reasons": {}
},
{
"tool": "randomize_tts_voice",
"tags": [],
"reasons": {}
},
{
"tool": "cycle_tts_voice",
"tags": [],
"reasons": {}
},
{
"tool": "enable_asr",
"tags": [],
"reasons": {}
},
{
"tool": "disable_asr",
"tags": [],
"reasons": {}
},
{
"tool": "change_asr",
"tags": [],
"reasons": {}
},
{
"tool": "configure_asr",
"tags": [],
"reasons": {}
},
{
"tool": "set_asr_mode",
"tags": [],
"reasons": {}
},
{
"tool": "set_tts_mode",
"tags": [],
"reasons": {}
},
{
"tool": "stop_voice_input",
"tags": [],
"reasons": {}
},
{
"tool": "get_dictated_text",
"tags": [],
"reasons": {}
},
{
"tool": "configure_communication",
"tags": [],
"reasons": {}
},
{
"tool": "send_whatsapp",
"tags": [],
"reasons": {}
},
{
"tool": "send_slack",
"tags": [],
"reasons": {}
},
{
"tool": "get_communication_status",
"tags": [],
"reasons": {}
},
{
"tool": "start_whatsapp_mode",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "stop_whatsapp_mode",
"tags": [],
"reasons": {}
},
{
"tool": "get_whatsapp_mode_status",
"tags": [],
"reasons": {}
},
{
"tool": "start_slack_mode",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "stop_slack_mode",
"tags": [],
"reasons": {}
},
{
"tool": "get_slack_mode_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_messages",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "432fe81fa3ff1f948ae6ca7fef8f78874547adcfb38cd6bc729db5de92092eb3",
"stats": {
"tools": 35,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 0,
"low": 0,
"info": 0
}
}
}