Chatcut — 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": "chatcut-mcp-server",
"source": {
"kind": "package",
"origin": "chatcut-mcp-server"
},
"server": {
"name": "chatcut-mcp-server"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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 execute shell commands or code"
],
"tags": [
"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 (22 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 (chatcut_mcp/hardware.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`chatcut_mcp/hardware.py:24`): 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": "chatcut_mcp/hardware.py"
},
"evidence": "try: res = subprocess.run( [\"ffmpeg\", \"-encoders\"], stdout=subprocess.PIPE,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "chatcut_mcp/hardware.py",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (chatcut_mcp/pptx_converter.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`chatcut_mcp/pptx_converter.py:28`): 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": "chatcut_mcp/pptx_converter.py"
},
"evidence": "] res = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=True)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "chatcut_mcp/pptx_converter.py",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (chatcut_mcp/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`chatcut_mcp/server.py:712`): 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": "chatcut_mcp/server.py"
},
"evidence": "res = subprocess.run(ffmpeg_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) if res.return",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "chatcut_mcp/server.py",
"line": 712,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (chatcut_mcp/transcriber.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`chatcut_mcp/transcriber.py:24`): 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": "chatcut_mcp/transcriber.py"
},
"evidence": "ut_audio_path ] subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, check=True) return outpu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "chatcut_mcp/transcriber.py",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (chatcut_mcp/video_composer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`chatcut_mcp/video_composer.py:22`): 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": "chatcut_mcp/video_composer.py"
},
"evidence": "] res = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=True)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "chatcut_mcp/video_composer.py",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"chatcut-mcp-server\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "chatcut-mcp-server"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "detect_hardware",
"tags": [],
"reasons": {}
},
{
"tool": "parse_video_guidelines_excel",
"tags": [],
"reasons": {}
},
{
"tool": "convert_pptx",
"tags": [],
"reasons": {}
},
{
"tool": "transcribe_video_file",
"tags": [],
"reasons": {}
},
{
"tool": "find_short_clips",
"tags": [],
"reasons": {}
},
{
"tool": "generate_vertical_crop_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "render_video_project",
"tags": [],
"reasons": {}
},
{
"tool": "add_background_music",
"tags": [],
"reasons": {}
},
{
"tool": "add_text_overlay",
"tags": [],
"reasons": {}
},
{
"tool": "add_pip_overlay",
"tags": [],
"reasons": {}
},
{
"tool": "generate_auto_subtitles",
"tags": [],
"reasons": {}
},
{
"tool": "add_zoom_effect",
"tags": [],
"reasons": {}
},
{
"tool": "add_transition",
"tags": [],
"reasons": {}
},
{
"tool": "generate_ai_image",
"tags": [],
"reasons": {}
},
{
"tool": "generate_ai_video",
"tags": [],
"reasons": {}
},
{
"tool": "generate_ai_speech",
"tags": [],
"reasons": {}
},
{
"tool": "download_video_asset",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "track_object_with_yolo",
"tags": [],
"reasons": {}
},
{
"tool": "add_visual_indicator",
"tags": [],
"reasons": {}
},
{
"tool": "add_dynamic_zoom",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_viral_cuts",
"tags": [],
"reasons": {}
},
{
"tool": "execute_video_pipeline",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c61b5b3c87a1c162f1b770c642e9d0f3318ee720b0cbc207e5dd9740be39be18",
"stats": {
"tools": 22,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 0,
"info": 1
}
}
}