Openlmlib — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "openlmlib",
"source": {
"kind": "package",
"origin": "openlmlib"
},
"server": {
"name": "openlmlib"
}
},
"grade": "B",
"score": {
"score": 84,
"threatScore": 91,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 9.45,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"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-1.8"
},
"capability": {
"level": "high",
"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"
],
"tags": [
"untrusted-input",
"external-sink",
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (60 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 (openlmlib/mcp_setup.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`openlmlib/mcp_setup.py:130`): 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": "openlmlib/mcp_setup.py"
},
"evidence": "atform env = env or dict(os.environ) home = Path(home) if home is not None else Path.home() if client_id ==",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "openlmlib/mcp_setup.py",
"line": 130,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (openlmlib/memory/retrogit_ingest.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`openlmlib/memory/retrogit_ingest.py:28`): 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": "openlmlib/memory/retrogit_ingest.py"
},
"evidence": "stdout.\"\"\" result = subprocess.run( [\"git\"] + args, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "openlmlib/memory/retrogit_ingest.py",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (openlmlib/tui_setup.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`openlmlib/tui_setup.py:32`): 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": "openlmlib/tui_setup.py"
},
"evidence": "} result = subprocess.run( [node, str(run_setup)], stdout=sys.stdout, stderr=sys.st",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "openlmlib/tui_setup.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([list_sessions, read_messages, tail_messages, read_message_range, list_findings]) co-exist with external-action tools ([send_message, export_to_library]). 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",
"name": "list_sessions → send_message"
},
"evidence": "untrusted [list_sessions, read_messages, tail_messages, read_message_range, list_findings] → sinks [send_message, export_to_library]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"list_sessions",
"read_messages",
"tail_messages",
"read_message_range",
"list_findings"
],
"sinks": [
"send_message",
"export_to_library"
]
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (openlmlib/embeddings.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`openlmlib/embeddings.py:30`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "openlmlib/embeddings.py"
},
"evidence": "self._cache = pickle.load(handle) except Exception: self._cache = {} self.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "openlmlib/embeddings.py",
"line": 30,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (openlmlib/vector_store.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`openlmlib/vector_store.py:178`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "openlmlib/vector_store.py"
},
"evidence": ": payload = pickle.load(handle) store = cls(int(payload[\"dim\"]), metric) store._vectors = pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "openlmlib/vector_store.py",
"line": 178,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"openlmlib\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "openlmlib"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"list_sessions",
"read_messages",
"tail_messages",
"read_message_range",
"list_findings"
],
"sensitiveSource": [],
"externalSink": [
"send_message",
"export_to_library"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "create_session",
"tags": [],
"reasons": {}
},
{
"tool": "join_session",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "collab_claim_task",
"tags": [],
"reasons": {}
},
{
"tool": "get_session_state",
"tags": [],
"reasons": {}
},
{
"tool": "update_session_state",
"tags": [],
"reasons": {}
},
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "read_messages",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "poll_messages",
"tags": [],
"reasons": {}
},
{
"tool": "tail_messages",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "read_message_range",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "grep_messages",
"tags": [],
"reasons": {}
},
{
"tool": "session_context",
"tags": [],
"reasons": {}
},
{
"tool": "save_artifact",
"tags": [],
"reasons": {}
},
{
"tool": "list_artifacts",
"tags": [],
"reasons": {}
},
{
"tool": "get_artifact",
"tags": [],
"reasons": {}
},
{
"tool": "grep_artifacts",
"tags": [],
"reasons": {}
},
{
"tool": "leave_session",
"tags": [],
"reasons": {}
},
{
"tool": "terminate_session",
"tags": [],
"reasons": {}
},
{
"tool": "export_to_library",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"export_to\""
]
}
},
{
"tool": "list_templates",
"tags": [],
"reasons": {}
},
{
"tool": "get_template",
"tags": [],
"reasons": {}
},
{
"tool": "create_from_template",
"tags": [],
"reasons": {}
},
{
"tool": "get_agent_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "sessions_summary",
"tags": [],
"reasons": {}
},
{
"tool": "search_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "session_relationships",
"tags": [],
"reasons": {}
},
{
"tool": "session_statistics",
"tags": [],
"reasons": {}
},
{
"tool": "list_models",
"tags": [],
"reasons": {}
},
{
"tool": "get_model_details",
"tags": [],
"reasons": {}
},
{
"tool": "recommended_models",
"tags": [],
"reasons": {}
},
{
"tool": "help_collab",
"tags": [],
"reasons": {}
},
{
"tool": "session_start",
"tags": [],
"reasons": {}
},
{
"tool": "session_end",
"tags": [],
"reasons": {}
},
{
"tool": "log_observation",
"tags": [],
"reasons": {}
},
{
"tool": "search_memory",
"tags": [],
"reasons": {}
},
{
"tool": "memory_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "get_observations",
"tags": [],
"reasons": {}
},
{
"tool": "query_memory",
"tags": [],
"reasons": {}
},
{
"tool": "inject_context",
"tags": [],
"reasons": {}
},
{
"tool": "session_recap",
"tags": [],
"reasons": {}
},
{
"tool": "topic_context",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_git_history",
"tags": [],
"reasons": {}
},
{
"tool": "init_library",
"tags": [],
"reasons": {}
},
{
"tool": "save_finding",
"tags": [],
"reasons": {}
},
{
"tool": "list_findings",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "get_finding",
"tags": [],
"reasons": {}
},
{
"tool": "search_findings",
"tags": [],
"reasons": {}
},
{
"tool": "retrieve_findings",
"tags": [],
"reasons": {}
},
{
"tool": "retrieve_context",
"tags": [],
"reasons": {}
},
{
"tool": "search_knowledge",
"tags": [],
"reasons": {}
},
{
"tool": "delete_finding",
"tags": [],
"reasons": {}
},
{
"tool": "health",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_retrieval",
"tags": [],
"reasons": {}
},
{
"tool": "start_research",
"tags": [],
"reasons": {}
},
{
"tool": "end_session",
"tags": [],
"reasons": {}
},
{
"tool": "check_context",
"tags": [],
"reasons": {}
},
{
"tool": "save_finding_auto",
"tags": [],
"reasons": {}
},
{
"tool": "help_library",
"tags": [],
"reasons": {}
},
{
"tool": "get_usage_analytics",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "430d0f18dd5c2d17fe1b6eb838ea9dcbcb50d653c7dcfbee9878ee52f1600cdf",
"stats": {
"tools": 60,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 3,
"low": 0,
"info": 1
}
}
}