Memorix — 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": "memorix",
"source": {
"kind": "package",
"origin": "memorix"
},
"server": {
"name": "memorix"
}
},
"grade": "B",
"score": {
"score": 84,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"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 (47 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/cli/memcode.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/memcode.js:2`): 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/memcode.js"
},
"evidence": "ync as __ms} from \"node:child_process\"; import {fileURLToPath as __fu} from \"node:url\"; if(!process.env.__MEMORIX_HEAP){",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/memcode.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/hermes/memorix/__init__.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/hermes/memorix/__init__.py:20`): 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": "plugins/hermes/memorix/__init__.py"
},
"evidence": "try: result = subprocess.run( command, input=input_data, capture_output=Tr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/hermes/memorix/__init__.py",
"line": 20,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/omp/memorix/extensions/memorix.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/omp/memorix/extensions/memorix.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": "plugins/omp/memorix/extensions/memorix.js"
},
"evidence": "spawnSync } from 'node:child_process'; const SESSION_ID = `omp-${Date.now().toString(36)}-${Math.random().toString(36)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/omp/memorix/extensions/memorix.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/openclaw/memorix/hooks/memorix/handler.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/openclaw/memorix/hooks/memorix/handler.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": "plugins/openclaw/memorix/hooks/memorix/handler.ts"
},
"evidence": "spawnSync } from 'node:child_process'; const SESSION_ID = `openclaw-${Date.now().toString(36)}-${Math.random().toStrin",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/openclaw/memorix/hooks/memorix/handler.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (plugins/pi/memorix/extensions/memorix.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`plugins/pi/memorix/extensions/memorix.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": "plugins/pi/memorix/extensions/memorix.js"
},
"evidence": "spawnSync } from 'node:child_process'; const SESSION_ID = `pi-${Date.now().toString(36)}-${Math.random().toString(36).",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "plugins/pi/memorix/extensions/memorix.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli/commands/agent-integrations.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli/commands/agent-integrations.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/cli/commands/agent-integrations.ts"
},
"evidence": "spawnSync } from 'node:child_process'; import { existsSync, realpathSync } from 'node:fs'; import { mkdir, readFile, wr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli/commands/agent-integrations.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli/commands/background.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli/commands/background.ts:24`): 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/cli/commands/background.ts"
},
"evidence": "ecFileSync } from 'node:child_process'; import { randomBytes } from 'node:crypto'; import os from 'node:os'; import { pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli/commands/background.ts",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli/commands/doctor.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli/commands/doctor.ts:54`): 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/cli/commands/doctor.ts"
},
"evidence": "} = await import('node:child_process'); const report: Record<string, unknown> = {}; const issues: string[] = [",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli/commands/doctor.ts",
"line": 54,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli/commands/hooks-install.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli/commands/hooks-install.ts:130`): 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/cli/commands/hooks-install.ts"
},
"evidence": "} = await import('node:child_process'); execSync('pwsh --version', { encoding: 'utf-8', tim",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli/commands/hooks-install.ts",
"line": 130,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/cli/tui/App.tsx)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/cli/tui/App.tsx:828`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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/cli/tui/App.tsx"
},
"evidence": "rd) { try { execSync(`start \"\" \"${background.dashboard}\"`, { stdio: 'pipe', windowsHide: true }); } catch {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/cli/tui/App.tsx",
"line": 828,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (src/cli/commands/setup.ts)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/cli/commands/setup.ts:11`): 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/cli/commands/setup.ts"
},
"evidence": "spawnSync } from 'node:child_process'; import { existsSync } from 'node:fs'; import { copyFile, mkdir, readFile, readdi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli/commands/setup.ts",
"line": 11,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "memorix_store",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_suggest_topic_key",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_search",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_graph_context",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_project_context",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_codegraph_status",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_context_pack",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_knowledge",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_resolve",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_store_reasoning",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_audit_project",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_search_reasoning",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_deduplicate",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_detail",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "memorix_retention",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_formation_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "create_entities",
"tags": [],
"reasons": {}
},
{
"tool": "create_relations",
"tags": [],
"reasons": {}
},
{
"tool": "add_observations",
"tags": [],
"reasons": {}
},
{
"tool": "delete_entities",
"tags": [],
"reasons": {}
},
{
"tool": "delete_observations",
"tags": [],
"reasons": {}
},
{
"tool": "delete_relations",
"tags": [],
"reasons": {}
},
{
"tool": "read_graph",
"tags": [],
"reasons": {}
},
{
"tool": "search_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "open_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_rules_sync",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_workspace_sync",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_skills",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_promote",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_consolidate",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_session_start",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_session_end",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_session_context",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_compaction_checkpoint",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_transfer",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_dashboard",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_evidence",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "team_manage",
"tags": [],
"reasons": {}
},
{
"tool": "team_file_lock",
"tags": [],
"reasons": {}
},
{
"tool": "team_task",
"tags": [],
"reasons": {}
},
{
"tool": "team_message",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "memorix_poll",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_handoff",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_media",
"tags": [],
"reasons": {}
},
{
"tool": "memorix_ingest_image",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9efcf3f1880431d77e8cb3f8a0c5c9421a74210ab76258e16a5ac2c62250b31c",
"stats": {
"tools": 47,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 1,
"low": 1,
"info": 0
}
}
}