Memlab — 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": "@memlab/mcp-server",
"source": {
"kind": "package",
"origin": "@memlab/mcp-server"
},
"server": {
"name": "@memlab/mcp-server"
}
},
"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": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (102 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-CAP-001",
"title": "Tool \"memlab_eval_across\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"memlab_eval_across\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "memlab_eval_across"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"memlab_eval\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"memlab_eval\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "memlab_eval"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/tools/eval.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/eval.js:2580`): 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/tools/eval.js"
},
"evidence": "ined_size` THROW inside eval (they read back ~0 on some loads). Use `helpers.retainedSize(id)` / `helpers.retainedSizes(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/tools/eval.js",
"line": 2580,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/tools/hypothesis.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/hypothesis.js:106`): 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/tools/hypothesis.js"
},
"evidence": "tests.push(vm.runInNewContext(`(function(node){ return !!(${spec.predicate}); })`, Object.create(null), { t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/tools/hypothesis.js",
"line": 106,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/memlab-cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/memlab-cli.js:36`): 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": "bin/memlab-cli.js"
},
"evidence": "/ import {spawn} from 'child_process'; import fs from 'fs'; import path from 'path'; import {fileURLToPath} from 'url';",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/memlab-cli.js",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/load-snapshot.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/load-snapshot.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/tools/load-snapshot.js"
},
"evidence": "{ execFileSync } from 'child_process'; import { z } from 'zod'; import memlabCore from '@memlab/core'; import memlabHea",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/load-snapshot.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"memlab_eval_across\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"memlab_eval_across\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "memlab_eval_across"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"memlab_eval\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"memlab_eval\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "memlab_eval"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "memlab_aggregate",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_analyze_run",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_anonymize_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_app_config",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_app_heap",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_array_group_by",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_artifact_budget",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_async_census",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_auto_investigate",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_batch",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_cache_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_census_diff",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_chain_walk",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_check_health",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_class_histogram",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_closure_inspection",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_collection_diff",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_collection_trend",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_detached_dom",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_dev_artifacts",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_diff_snapshots",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_dom_audit",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_dominator_attribution",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_dominator_chain",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_dominator_subtree",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_duplicate_objects",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_duplicated_strings",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_eval_across",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "memlab_eval",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "memlab_event_listener_leaks",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_event_registry",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_explain_delta",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_find_by_property",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_find_by_shape",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_find_nodes_by_class",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_finding_index",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_for_each",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_get_node",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_get_property",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_get_references",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_get_referrers",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_get_string",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_get_value",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_global_variables",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_growth_signals",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_hunt_report",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_hypothesis",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_id_space_audit",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_identify",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_identity_diff",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_intern_opportunities",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_ladder_probe",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_ladder",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_largest_objects",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_leak_report",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_load_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_map_entries",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_match_object",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_metric",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_module_attribution",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_next_measurement",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_object_cost_breakdown",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_object_shape",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_pinch_points",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_population_diff",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_population_vs_owners",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_property_distribution",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_property_names",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_quick_diagnosis",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_react_owners",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_react_update_queues",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_referrer_summary",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_replicate",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_reports",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_retainer_diff",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_retainer_layers",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_retainer_summary",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_retainer_trace",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_round_audit",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_round_digest",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_script_census",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_search_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_search_strings",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_sequence_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_server_status",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_settle_check",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_shape_histogram",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_sliced_strings",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_snapshot_header",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_snapshot_summary",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_snapshots",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_sparse_elements",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_stale_collections",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_string_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_tools",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_trace_all",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_trace_dominators",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_unit_cost",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_verify_fix",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_weakmap_entries",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_weakref_census",
"tags": [],
"reasons": {}
},
{
"tool": "memlab_what_if",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "f7b9ffbcc2aa87dc1dddacc6624f341d64ab6e19176840209dc3ea2b43de54e3",
"stats": {
"tools": 102,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 2,
"info": 0
}
}
}