Simply — 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": "simply-mcp",
"source": {
"kind": "package",
"origin": "simply-mcp"
},
"server": {
"name": "simply-mcp"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (1 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-001",
"title": "Dynamic code execution in server code (dist/src/client/RemoteDOMRenderer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/client/RemoteDOMRenderer.js:672`): 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/src/client/RemoteDOMRenderer.js"
},
"evidence": "{ const func = new Function('remoteDOM', 'console', '\"use strict\"; ' + script); func(remoteDOM, console",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/src/client/RemoteDOMRenderer.js",
"line": 672,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/src/client/remote-dom/RemoteDOMWorkerManager.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/client/remote-dom/RemoteDOMWorkerManager.js:402`): 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/src/client/remote-dom/RemoteDOMWorkerManager.js"
},
"evidence": "const func = new Function('remoteRoot', 'console', '\"use strict\";\\\\n' + code); func(remoteRoot, con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/src/client/remote-dom/RemoteDOMWorkerManager.js",
"line": 402,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/src/client/remote-dom/csp-validator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/client/remote-dom/csp-validator.js:94`): 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/src/client/remote-dom/csp-validator.js"
},
"evidence": "blockedValue: 'new Function()', reason: \"Function() constructor is blocked by CSP. Use safer al",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/src/client/remote-dom/csp-validator.js",
"line": 94,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/src/client/remote-dom/sandbox-worker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/client/remote-dom/sandbox-worker.js:248`): 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/src/client/remote-dom/sandbox-worker.js"
},
"evidence": "c. const func = new Function('remoteDOM', 'console', `\"use strict\"; ${script}`); // Execute with restric",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/src/client/remote-dom/sandbox-worker.js",
"line": 248,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/src/client/remote-dom/worker/remote-dom-worker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/client/remote-dom/worker/remote-dom-worker.js:169`): 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/src/client/remote-dom/worker/remote-dom-worker.js"
},
"evidence": "onst isolatedFunction = new Function('remoteRoot', 'console', '\"use strict\";\\n' + code); // Execute with control",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/src/client/remote-dom/worker/remote-dom-worker.js",
"line": 169,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/cli/dependency-manager.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/cli/dependency-manager.js:17`): 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/src/cli/dependency-manager.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { readFile, stat, rm } from 'node:fs/promises'; import { existsSync } fro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/cli/dependency-manager.js",
"line": 17,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/cli/interface-bin.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/cli/interface-bin.js:100`): 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/src/cli/interface-bin.js"
},
"evidence": "} = await import('node:child_process'); const nodeArgs = ['--import', 'tsx']; const scriptPath = fileUR",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/cli/interface-bin.js",
"line": 100,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/cli/multi-server-runner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/cli/multi-server-runner.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": "dist/src/cli/multi-server-runner.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { resolve, basename } from 'node:path'; import { existsSync } from 'node:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/cli/multi-server-runner.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/cli/run.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/cli/run.js:8`): 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/src/cli/run.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { loadCLIConfig, mergeRunConfig, mergeServerConfig, getConfigFilePath, re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/cli/run.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/cli/watch-mode.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/cli/watch-mode.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": "dist/src/cli/watch-mode.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { resolve, dirname, join } from 'node:path'; import { fileURLToPath } fro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/cli/watch-mode.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/core/formatters/watch-manager.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/core/formatters/watch-manager.js:6`): 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/src/core/formatters/watch-manager.js"
},
"evidence": "import { spawn } from 'child_process'; /** * Global server process reference for restarts */ let serverProcess = null",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/core/formatters/watch-manager.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/core/typescript-detector.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/core/typescript-detector.js:70`): 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/src/core/typescript-detector.js"
},
"evidence": "cSync } = getRequire()('child_process'); // Use stdio: 'pipe' to suppress output and just check exit code",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/core/typescript-detector.js",
"line": 70,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/features/dependencies/dependency-installer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/features/dependencies/dependency-installer.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": "dist/src/features/dependencies/dependency-installer.js"
},
"evidence": "import { spawn } from 'child_process'; import { access } from 'fs/promises'; import { join } from 'path'; import { dete",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/features/dependencies/dependency-installer.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/features/dependencies/dependency-resolver.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/features/dependencies/dependency-resolver.js:252`): 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/src/features/dependencies/dependency-resolver.js"
},
"evidence": "'buffer', 'child_process', 'cluster', 'crypto', 'dgram', 'dns', 'ev",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/features/dependencies/dependency-resolver.js",
"line": 252,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/src/features/dependencies/package-manager-detector.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/features/dependencies/package-manager-detector.js:7`): 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/src/features/dependencies/package-manager-detector.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); /** * Dete",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/src/features/dependencies/package-manager-detector.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/cli/cli-config-loader.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/cli/cli-config-loader.js:79`): 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": "dist/src/cli/cli-config-loader.js"
},
"evidence": "const module = await import(configUrl); const config = module.default || module; validateCLIC",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/cli/cli-config-loader.js",
"line": 79,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/cli/dry-run.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/cli/dry-run.js:56`): 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": "dist/src/cli/dry-run.js"
},
"evidence": "module = await import(fileUrl); } else { // Fallback to tsImport API (for backwards",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/cli/dry-run.js",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/cli/interface-bin.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/cli/interface-bin.js:21`): 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": "dist/src/cli/interface-bin.js"
},
"evidence": "f; return await import(fileUrl); } // Fallback to tsImport API (for backwards compatibility) try {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/cli/interface-bin.js",
"line": 21,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/cli/run.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/cli/run.js:58`): 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": "dist/src/cli/run.js"
},
"evidence": "module = await import(fileUrl); } else { // Fallback to tsImport API (for backwards",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/cli/run.js",
"line": 58,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/config/config-loader.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/config/config-loader.js:132`): 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": "dist/src/config/config-loader.js"
},
"evidence": "const module = await import(configUrl); // Handle default export or named export const config = modul",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/config/config-loader.js",
"line": 132,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/core/config-loader.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/core/config-loader.js:77`): 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": "dist/src/core/config-loader.js"
},
"evidence": "const module = await import(configUrl); const config = module.default || module; validateConf",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/core/config-loader.js",
"line": 77,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/handlers/FileHandlerResolver.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/handlers/FileHandlerResolver.js:82`): 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": "dist/src/handlers/FileHandlerResolver.js"
},
"evidence": "const module = await import(fileUrl); // Cache the loaded module this.moduleCache.set(filePat",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/handlers/FileHandlerResolver.js",
"line": 82,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/server/adapter.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/server/adapter.js:114`): 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": "dist/src/server/adapter.js"
},
"evidence": "const module = await import(moduleUrl); let ServerClass = module.default; // Handle CommonJS bundles: When im",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/server/adapter.js",
"line": 114,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/src/server/test-utils.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/src/server/test-utils.js:48`): 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": "dist/src/server/test-utils.js"
},
"evidence": "const module = await import(moduleUrl); // Get the default export (server class or instance) or use module di",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/src/server/test-utils.js",
"line": 48,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "greet",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "5b102527b3f9f9b67e1d651a25c321eb337ec98313aa77dcca4dc542cc436819",
"stats": {
"tools": 1,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 15,
"medium": 9,
"low": 0,
"info": 0
}
}
}