Erdl — the complete, unedited output of the deterministic mcptrustchecker engine v1.5.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.5.0",
"methodologyVersion": "mcptrustchecker-1.4"
},
"target": {
"id": "@openoba-ai/erdl-mcp",
"source": {
"kind": "package",
"origin": "@openoba-ai/erdl-mcp"
},
"server": {
"name": "@openoba-ai/erdl-mcp"
}
},
"grade": "C",
"score": {
"score": 71,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 23.1,
"exfiltration": 0,
"permissions": 6.3,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"ruleId": "MTC-SRC-010",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"ruleId": "MTC-SRC-010",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 7.7
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/engine/safe-expr.d.ts)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/safe-expr.d.ts:27`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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": "dist/engine/safe-expr.d.ts"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/engine/safe-expr.d.ts",
"line": 27
}
},
{
"ruleId": "MTC-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/engine/safe-expr.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/safe-expr.js:225`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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": "dist/engine/safe-expr.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/engine/safe-expr.js",
"line": 225
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/engine/safe-expr.d.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/safe-expr.d.ts:6`): 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": "dist/engine/safe-expr.d.ts"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/engine/safe-expr.d.ts",
"line": 6
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/engine/safe-expr.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/safe-expr.js:6`): 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": "dist/engine/safe-expr.js"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/engine/safe-expr.js",
"line": 6
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (bin/erdl-mcp.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`bin/erdl-mcp.js:27`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/erdl-mcp.js"
},
"evidence": "import(resolved)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "bin/erdl-mcp.js",
"line": 27
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (dist/engine/rule-store.js)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/rule-store.js:157`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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/engine/rule-store.js"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "dist/engine/rule-store.js",
"line": 157
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "9a77bc20ff407d10ac198b36e3420a421ab3636e3d9b0725656ee3e30db4bfb6",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 2,
"low": 0,
"info": 0
}
}
}