Neurolisp — the complete, unedited output of the deterministic mcptrustchecker engine v1.7.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.7.0",
"methodologyVersion": "mcptrustchecker-1.7"
},
"target": {
"id": "neurolisp",
"source": {
"kind": "package",
"origin": "neurolisp"
},
"server": {
"name": "neurolisp"
}
},
"grade": "D",
"score": {
"score": 68,
"threatScore": 83,
"grade": "D",
"band": "D",
"categorySubtotals": {
"injection": 15.4,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 2.1,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-010",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"kind": "threat",
"ruleId": "MTC-SUP-011",
"category": "supply-chain",
"severity": "low",
"confidence": "strong",
"rawWeight": 3,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 2.1
},
{
"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": "none",
"label": "publisher verification (unlocatable) — no provenance and no public repository to inspect",
"appliedPenalty": 5
},
{
"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-1.7"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"tags": [
"external-sink",
"untrusted-input",
"code-exec",
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (57 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-006",
"title": "Reads a sensitive credential path or dumps the environment (tests/test_v26_19_hash_cross_process_stability.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_v26_19_hash_cross_process_stability.py:25`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "tests/test_v26_19_hash_cross_process_stability.py"
},
"evidence": "dict(os.environ)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/test_v26_19_hash_cross_process_stability.py",
"line": 25
}
},
{
"ruleId": "MTC-SRC-010",
"title": "Dynamic evaluation of a non-literal value (neurolisp/self_optimize.py)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`neurolisp/self_optimize.py:349`): 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": "neurolisp/self_optimize.py"
},
"evidence": "eval\n (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "neurolisp/self_optimize.py",
"line": 349
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nl_query_skill\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nl_query_skill\" appears to run shell commands or evaluate code (keyword \"eval\"). 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": "nl_query_skill"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nl_eval_sexpr\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nl_eval_sexpr\" appears to run shell commands or evaluate code (keyword \"eval\"). 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": "nl_eval_sexpr"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nl_crystallize_now\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nl_crystallize_now\" appears to run shell commands or evaluate code (keyword \"eval\"). 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": "nl_crystallize_now"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nl_self_test\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nl_self_test\" appears to run shell commands or evaluate code (keyword \"shell\"). 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": "nl_self_test"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"nl_list_primitives\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"nl_list_primitives\" appears to run shell commands or evaluate code (keyword \"eval\"). 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": "nl_list_primitives"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (neurolisp/self_optimize.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`neurolisp/self_optimize.py:349`): 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": "neurolisp/self_optimize.py"
},
"evidence": "eval\n (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "neurolisp/self_optimize.py",
"line": 349
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/test_v5_homoiconicity.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_v5_homoiconicity.py:43`): 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": "tests/test_v5_homoiconicity.py"
},
"evidence": "eval (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/test_v5_homoiconicity.py",
"line": 43
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (tests/test_v5_sexpr_tools.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_v5_sexpr_tools.py:100`): 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": "tests/test_v5_sexpr_tools.py"
},
"evidence": "eval (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/test_v5_sexpr_tools.py",
"line": 100
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tests/test_v26_19_hash_cross_process_stability.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_v26_19_hash_cross_process_stability.py:27`): 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": "tests/test_v26_19_hash_cross_process_stability.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_v26_19_hash_cross_process_stability.py",
"line": 27
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([nl_load_template]) co-exist with external-action tools ([nl_open_task, nl_query_skill, nl_eval_sexpr, nl_crystallize_now, nl_self_test, nl_list_primitives]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow"
},
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"nl_load_template"
],
"sinks": [
"nl_open_task",
"nl_query_skill",
"nl_eval_sexpr",
"nl_crystallize_now",
"nl_self_test",
"nl_list_primitives"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nl_query_skill\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nl_query_skill\" 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": "nl_query_skill"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nl_eval_sexpr\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nl_eval_sexpr\" 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": "nl_eval_sexpr"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nl_crystallize_now\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nl_crystallize_now\" 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": "nl_crystallize_now"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nl_self_test\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nl_self_test\" 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": "nl_self_test"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"nl_list_primitives\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"nl_list_primitives\" 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": "nl_list_primitives"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package has no source repository",
"category": "supply-chain",
"severity": "low",
"confidence": "strong",
"description": "\"neurolisp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "neurolisp"
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"neurolisp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "neurolisp"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"nl_load_template"
],
"sensitiveSource": [],
"externalSink": [
"nl_open_task",
"nl_query_skill",
"nl_eval_sexpr",
"nl_crystallize_now",
"nl_self_test",
"nl_list_primitives"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "nl_focus",
"tags": [],
"reasons": {}
},
{
"tool": "nl_open_task",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"request\""
]
}
},
{
"tool": "nl_close_task",
"tags": [],
"reasons": {}
},
{
"tool": "nl_corpus_find",
"tags": [],
"reasons": {}
},
{
"tool": "nl_fulltext_search",
"tags": [],
"reasons": {}
},
{
"tool": "nl_get_sop_warnings",
"tags": [],
"reasons": {}
},
{
"tool": "nl_pattern_find",
"tags": [],
"reasons": {}
},
{
"tool": "nl_tag",
"tags": [],
"reasons": {}
},
{
"tool": "nl_untag",
"tags": [],
"reasons": {}
},
{
"tool": "nl_list_tags",
"tags": [],
"reasons": {}
},
{
"tool": "nl_row_tags",
"tags": [],
"reasons": {}
},
{
"tool": "nl_anti_unify",
"tags": [],
"reasons": {}
},
{
"tool": "nl_save_template",
"tags": [],
"reasons": {}
},
{
"tool": "nl_load_template",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "nl_delete_template",
"tags": [],
"reasons": {}
},
{
"tool": "nl_list_saved_templates",
"tags": [],
"reasons": {}
},
{
"tool": "nl_find_by_template",
"tags": [],
"reasons": {}
},
{
"tool": "nl_query_skill",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\""
]
}
},
{
"tool": "nl_eval_sexpr",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\""
]
}
},
{
"tool": "nl_resolve_subagent",
"tags": [],
"reasons": {}
},
{
"tool": "nl_record",
"tags": [],
"reasons": {}
},
{
"tool": "nl_correct",
"tags": [],
"reasons": {}
},
{
"tool": "nl_crystallize_now",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\""
]
}
},
{
"tool": "nl_retire_stale",
"tags": [],
"reasons": {}
},
{
"tool": "nl_mcp_manifest",
"tags": [],
"reasons": {}
},
{
"tool": "nl_status_report",
"tags": [],
"reasons": {}
},
{
"tool": "nl_self_test",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\""
]
}
},
{
"tool": "nl_subagent_reputation",
"tags": [],
"reasons": {}
},
{
"tool": "nl_health",
"tags": [],
"reasons": {}
},
{
"tool": "nl_trace_optimizer_proposals",
"tags": [],
"reasons": {}
},
{
"tool": "nl_list_primitives",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\""
]
}
},
{
"tool": "nl_workflow_replay",
"tags": [],
"reasons": {}
},
{
"tool": "nl_trace_provenance",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_artifact",
"tags": [],
"reasons": {}
},
{
"tool": "nl_list_template_history",
"tags": [],
"reasons": {}
},
{
"tool": "nl_restore_template",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_status",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_list",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_checkpoints",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_checkpoint_dag",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_trace_spans",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_diff",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_audit_report",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_interrupt",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_resume",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_approval_respond",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_run_with_review",
"tags": [],
"reasons": {}
},
{
"tool": "nl_fork_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "nl_grade_and_select",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_patch_step",
"tags": [],
"reasons": {}
},
{
"tool": "nl_workflow_review",
"tags": [],
"reasons": {}
},
{
"tool": "nl_apply_coverage_detector",
"tags": [],
"reasons": {}
},
{
"tool": "nl_get_playbook",
"tags": [],
"reasons": {}
},
{
"tool": "nl_send_to",
"tags": [],
"reasons": {}
},
{
"tool": "nl_read_inbox",
"tags": [],
"reasons": {}
},
{
"tool": "nl_peek_inbox",
"tags": [],
"reasons": {}
},
{
"tool": "nl_inbox_size",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "bf21159091de17d3c003ce7b90ff13d81047eaa6e3ddf8cf21aa26487472aa46",
"stats": {
"tools": 57,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 11,
"medium": 1,
"low": 6,
"info": 1
}
}
}