Galaxy — 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": "galaxy-mcp",
"source": {
"kind": "package",
"origin": "galaxy-mcp"
},
"server": {
"name": "galaxy-mcp"
}
},
"grade": "A",
"score": {
"score": 96,
"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": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"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": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service"
],
"tags": [
"external-sink",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (45 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-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([download_dataset, get_iwc_workflows, get_page, list_page_revisions, get_page_revision]) co-exist with external-action tools ([create_history, upload_file, upload_file_from_url]). 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": "download_dataset → create_history"
},
"evidence": "untrusted [download_dataset, get_iwc_workflows, get_page, list_page_revisions, get_page_revision] → sinks [create_history, upload_file, upload_file_from_url]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"download_dataset",
"get_iwc_workflows",
"get_page",
"list_page_revisions",
"get_page_revision"
],
"sinks": [
"create_history",
"upload_file",
"upload_file_from_url"
]
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/galaxy_mcp/server.py)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/galaxy_mcp/server.py:2321`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/galaxy_mcp/server.py"
},
"evidence": ", Any]]: response = requests.get(\"https://iwc.galaxyproject.org/workflow_manifest.json\") response.raise_for_stat",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/galaxy_mcp/server.py",
"line": 2321,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_discovery_mode.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_discovery_mode.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": "tests/test_discovery_mode.py"
},
"evidence": "\"\"\" ) result = subprocess.run( [sys.executable, \"-c\", script], env=env, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_discovery_mode.py",
"line": 32,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"galaxy-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "galaxy-mcp"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"download_dataset",
"get_iwc_workflows",
"get_page",
"list_page_revisions",
"get_page_revision"
],
"sensitiveSource": [],
"externalSink": [
"create_history",
"upload_file",
"upload_file_from_url"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "connect",
"tags": [],
"reasons": {}
},
{
"tool": "search_tools_by_name",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_run_examples",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_input_template",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_citations",
"tags": [],
"reasons": {}
},
{
"tool": "run_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_panel",
"tags": [],
"reasons": {}
},
{
"tool": "create_history",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "update_history",
"tags": [],
"reasons": {}
},
{
"tool": "search_tools_by_keywords",
"tags": [],
"reasons": {}
},
{
"tool": "get_server_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_user",
"tags": [],
"reasons": {}
},
{
"tool": "get_histories",
"tags": [],
"reasons": {}
},
{
"tool": "list_history_ids",
"tags": [],
"reasons": {}
},
{
"tool": "get_history_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_history_contents",
"tags": [],
"reasons": {}
},
{
"tool": "get_job_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_dataset_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_collection_details",
"tags": [],
"reasons": {}
},
{
"tool": "download_dataset",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "upload_file_from_url",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "get_invocations",
"tags": [],
"reasons": {}
},
{
"tool": "get_iwc_workflows",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "search_iwc_workflows",
"tags": [],
"reasons": {}
},
{
"tool": "get_iwc_workflow_details",
"tags": [],
"reasons": {}
},
{
"tool": "recommend_iwc_workflows",
"tags": [],
"reasons": {}
},
{
"tool": "import_workflow_from_iwc",
"tags": [],
"reasons": {}
},
{
"tool": "list_workflows",
"tags": [],
"reasons": {}
},
{
"tool": "get_workflow_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_workflow_input_template",
"tags": [],
"reasons": {}
},
{
"tool": "invoke_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_workflow_invocation",
"tags": [],
"reasons": {}
},
{
"tool": "create_user_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_user_tools",
"tags": [],
"reasons": {}
},
{
"tool": "delete_user_tool",
"tags": [],
"reasons": {}
},
{
"tool": "run_user_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_pages",
"tags": [],
"reasons": {}
},
{
"tool": "get_page",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "create_page",
"tags": [],
"reasons": {}
},
{
"tool": "update_page",
"tags": [],
"reasons": {}
},
{
"tool": "list_page_revisions",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_page_revision",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "revert_page_revision",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c1d86f2fe0f0378a24cffcc92c370be1ce0d686c8e43b3faa293b9ac53c5c7f0",
"stats": {
"tools": 45,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 2,
"low": 1,
"info": 1
}
}
}