Autobeat — 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": "autobeat",
"source": {
"kind": "package",
"origin": "autobeat"
},
"server": {
"name": "autobeat"
}
},
"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-1.13"
},
"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-001",
"title": "Dynamic code execution in server code (dist/cli/commands/loop.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands/loop.js:93`): 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/cli/commands/loop.js"
},
"evidence": "mize is required with --eval (optimize strategy)'); } if (!isOptimize && direction) { return err('--mini",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/cli/commands/loop.js",
"line": 93,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/cli/commands/schedule.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands/schedule.js:272`): 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/cli/commands/schedule.js"
},
"evidence": "mize is required with --eval (optimize strategy)'); } if (!isOptimize && lf.loopDirection) {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/cli/commands/schedule.js",
"line": 272,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/commands/agents.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands/agents.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/cli/commands/agents.js"
},
"evidence": "ort { spawnSync } from 'child_process'; import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'fs'; import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/commands/agents.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/commands/mcp.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands/mcp.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/cli/commands/mcp.js"
},
"evidence": "import { spawn } from 'child_process'; import path from 'path'; import { errorMessage } from '../services.js'; import *",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/commands/mcp.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/commands/schedule-executor.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/commands/schedule-executor.js:124`): 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/cli/commands/schedule-executor.js"
},
"evidence": "} = await import('node:child_process'); // Spawn the executor as a detached background process // Uses the same",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/commands/schedule-executor.js",
"line": 124,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/detach-helpers.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/detach-helpers.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/cli/detach-helpers.js"
},
"evidence": "import { spawn } from 'child_process'; import { closeSync, mkdirSync, openSync, readFileSync } from 'fs'; import { home",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/detach-helpers.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/core/agents.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/core/agents.js:10`): 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/core/agents.js"
},
"evidence": "ort { spawnSync } from 'child_process'; import { AutobeatError, ErrorCode } from './errors.js'; import { err, ok } from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/core/agents.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/implementations/base-agent-adapter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/implementations/base-agent-adapter.js:14`): 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/implementations/base-agent-adapter.js"
},
"evidence": "import { spawn } from 'child_process'; import os from 'os'; import path from 'path'; import { AGENT_AUTH, AGENT_BASE_UR",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/implementations/base-agent-adapter.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/implementations/event-driven-worker-pool.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/implementations/event-driven-worker-pool.js:29`): 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/implementations/event-driven-worker-pool.js"
},
"evidence": "valMs); } async spawn(task) { this.logger.debug('Spawning worker for task', { taskId: task.i",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/implementations/event-driven-worker-pool.js",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/implementations/process-spawner-adapter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/implementations/process-spawner-adapter.js:19`): 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/implementations/process-spawner-adapter.js"
},
"evidence": "r = provider; } spawn(options) { return this.spawner.spawn(options); } spawnInteractive(_options",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/implementations/process-spawner-adapter.js",
"line": 19,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/services/exit-condition-evaluator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/services/exit-condition-evaluator.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/services/exit-condition-evaluator.js"
},
"evidence": "exec as cpExec } from 'child_process'; import { promisify } from 'util'; import { LoopStrategy } from '../core/domain.j",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/services/exit-condition-evaluator.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/utils/git-state.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/utils/git-state.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/utils/git-state.js"
},
"evidence": "port { execFile } from 'child_process'; import { promisify } from 'util'; import { AutobeatError, ErrorCode } from '../c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/utils/git-state.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/cli/commands/mcp.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/cli/commands/mcp.js:47`): 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/cli/commands/mcp.js"
},
"evidence": "rname, 'index.js'); import(indexPath) .then((module) => { if (module.main) { return modu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/cli/commands/mcp.js",
"line": 47,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "ac8200fd3551ca61a35e6eb72d96ecfb490cfde28b5884eabd4f622084c3e6a1",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 12,
"medium": 1,
"low": 0,
"info": 0
}
}
}