Rubber Duck — the complete, unedited output of the deterministic mcptrustchecker engine v1.7.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.7.0",
"methodologyVersion": "mcptrustchecker-1.7"
},
"target": {
"id": "mcp-rubber-duck",
"source": {
"kind": "package",
"origin": "mcp-rubber-duck"
},
"server": {
"name": "mcp-rubber-duck"
}
},
"grade": "A",
"score": {
"score": 90,
"threatScore": 96,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 3.6,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-TARGET-2",
"category": "injection",
"severity": "medium",
"confidence": "heuristic",
"rawWeight": 9,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 3.6
},
{
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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-1.7"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (10 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 (dist/providers/cli/process-runner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/providers/cli/process-runner.js:1`): 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/providers/cli/process-runner.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/providers/cli/process-runner.js",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/providers/cli/process-runner.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/providers/cli/process-runner.ts:1`): 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": "src/providers/cli/process-runner.ts"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/providers/cli/process-runner.ts",
"line": 1
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (test-mcp-interface.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`test-mcp-interface.js:5`): 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": "test-mcp-interface.js"
},
"evidence": "child_process",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test-mcp-interface.js",
"line": 5
}
},
{
"ruleId": "MTC-INJ-TARGET-2",
"title": "Solicitation of model context / history",
"category": "injection",
"severity": "medium",
"confidence": "heuristic",
"description": "Solicitation of model context / history detected in the description of tool \"clear_conversations\". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "tool",
"name": "clear_conversations",
"field": "description"
},
"evidence": "conversation history",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "sensitive-target"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "ask_duck",
"tags": [],
"reasons": {}
},
{
"tool": "chat_with_duck",
"tags": [],
"reasons": {}
},
{
"tool": "clear_conversations",
"tags": [],
"reasons": {}
},
{
"tool": "list_ducks",
"tags": [],
"reasons": {}
},
{
"tool": "list_models",
"tags": [],
"reasons": {}
},
{
"tool": "duck_council",
"tags": [],
"reasons": {}
},
{
"tool": "duck_judge",
"tags": [],
"reasons": {}
},
{
"tool": "get_pending_approvals",
"tags": [],
"reasons": {}
},
{
"tool": "approve_mcp_request",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"request\""
]
}
},
{
"tool": "mcp_status",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "22c7fd0245949856fa7ccad4c1831bb73657869de402c2bc06d8b29047099669",
"stats": {
"tools": 10,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 1,
"low": 0,
"info": 0
}
}
}