Claude Smalltalk — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "claude-smalltalk",
"source": {
"kind": "package",
"origin": "claude-smalltalk"
},
"server": {
"name": "claude-smalltalk"
}
},
"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-1.9"
},
"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 (12 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 (claude_smalltalk/openai_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`claude_smalltalk/openai_mcp.py:58`): 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": "claude_smalltalk/openai_mcp.py"
},
"evidence": "self.process = subprocess.Popen( [self.vm_path, self.image_path, \"--mcp\"], stdin=subpro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "claude_smalltalk/openai_mcp.py",
"line": 58,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (clawdbot/smalltalk-daemon.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`clawdbot/smalltalk-daemon.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": "clawdbot/smalltalk-daemon.py"
},
"evidence": "self.process = subprocess.Popen( cmd, stdin=subprocess.PIPE, st",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "clawdbot/smalltalk-daemon.py",
"line": 101,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (clawdbot/smalltalk.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`clawdbot/smalltalk.py:192`): 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": "clawdbot/smalltalk.py"
},
"evidence": "y: result = subprocess.run( [\"xvfb-run\", \"-a\", vm_path, image_path, \"--mcp\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "clawdbot/smalltalk.py",
"line": 192,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (openai_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`openai_mcp.py:59`): 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": "openai_mcp.py"
},
"evidence": "self.process = subprocess.Popen( [self.vm_path, self.image_path, \"--mcp\"], stdin=subpro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "openai_mcp.py",
"line": 59,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "smalltalk_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_browse",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "smalltalk_method_source",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_define_class",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_define_method",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_delete_method",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_delete_class",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_list_classes",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_hierarchy",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_subclasses",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_list_categories",
"tags": [],
"reasons": {}
},
{
"tool": "smalltalk_classes_in_category",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9d4f1c33b77ed33f072ef706ea4d968dcfb10eac7d58e5be5db4c5315541266f",
"stats": {
"tools": 12,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 0,
"info": 0
}
}
}