Work Graph — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "@work-graph/mcp",
"source": {
"kind": "package",
"origin": "@work-graph/mcp"
},
"server": {
"name": "@work-graph/mcp"
}
},
"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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"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 (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-FLOW-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([onebase_read_config_file]) and tools that can send data out ([get_operator_shell_snapshot]) are exposed together. An agent can move private data to the sink.",
"remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
"location": {
"kind": "flow",
"name": "onebase_read_config_file → get_operator_shell_snapshot"
},
"evidence": "sources [onebase_read_config_file] → sinks [get_operator_shell_snapshot]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"onebase_read_config_file"
],
"sinks": [
"get_operator_shell_snapshot"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"get_operator_shell_snapshot\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"get_operator_shell_snapshot\" appears to run shell commands or evaluate code (keyword \"shell\" 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": "get_operator_shell_snapshot"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"get_operator_shell_snapshot\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"get_operator_shell_snapshot\" 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": "get_operator_shell_snapshot"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"onebase_read_config_file"
],
"externalSink": [
"get_operator_shell_snapshot"
],
"selfContained": false,
"path": [
"onebase_read_config_file",
"get_operator_shell_snapshot"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: onebase_read_config_file → get_operator_shell_snapshot."
}
],
"capabilities": [
{
"tool": "list_work_items",
"tags": [],
"reasons": {}
},
{
"tool": "get_work_item",
"tags": [],
"reasons": {}
},
{
"tool": "get_backlog_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "get_current_cycle",
"tags": [],
"reasons": {}
},
{
"tool": "get_promote_ready_queue",
"tags": [],
"reasons": {}
},
{
"tool": "get_intent_hierarchy",
"tags": [],
"reasons": {}
},
{
"tool": "get_architecture_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "get_unified_linkage",
"tags": [],
"reasons": {}
},
{
"tool": "query_intent_plane",
"tags": [],
"reasons": {}
},
{
"tool": "query_semantic_field",
"tags": [],
"reasons": {}
},
{
"tool": "detect_semantic_drift",
"tags": [],
"reasons": {}
},
{
"tool": "get_context_slice",
"tags": [],
"reasons": {}
},
{
"tool": "find_semantic_voids",
"tags": [],
"reasons": {}
},
{
"tool": "get_epic_work_scope",
"tags": [],
"reasons": {}
},
{
"tool": "get_pvrg_task_scope",
"tags": [],
"reasons": {}
},
{
"tool": "get_graph_rag_context",
"tags": [],
"reasons": {}
},
{
"tool": "list_memory_records",
"tags": [],
"reasons": {}
},
{
"tool": "get_memory_record",
"tags": [],
"reasons": {}
},
{
"tool": "list_evidence_records",
"tags": [],
"reasons": {}
},
{
"tool": "get_evidence_record",
"tags": [],
"reasons": {}
},
{
"tool": "get_operator_shell_snapshot",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\" in tool name"
]
}
},
{
"tool": "get_step_graph_projection",
"tags": [],
"reasons": {}
},
{
"tool": "get_step_graph_slice",
"tags": [],
"reasons": {}
},
{
"tool": "update_work_item_status",
"tags": [],
"reasons": {}
},
{
"tool": "add_work_item_evidence",
"tags": [],
"reasons": {}
},
{
"tool": "claim_work_item",
"tags": [],
"reasons": {}
},
{
"tool": "complete_work_item",
"tags": [],
"reasons": {}
},
{
"tool": "git_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "get_work_contract",
"tags": [],
"reasons": {}
},
{
"tool": "assert_task_ready_for_done",
"tags": [],
"reasons": {}
},
{
"tool": "validate_evidence",
"tags": [],
"reasons": {}
},
{
"tool": "get_analytics_lineage",
"tags": [],
"reasons": {}
},
{
"tool": "create_work_item",
"tags": [],
"reasons": {}
},
{
"tool": "get_work_item_pipeline",
"tags": [],
"reasons": {}
},
{
"tool": "record_work_item_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "record_work_item_decision",
"tags": [],
"reasons": {}
},
{
"tool": "list_work_item_ui_references",
"tags": [],
"reasons": {}
},
{
"tool": "attach_work_item_ui_reference",
"tags": [],
"reasons": {}
},
{
"tool": "read_work_item_atom",
"tags": [],
"reasons": {}
},
{
"tool": "semantic_search",
"tags": [],
"reasons": {}
},
{
"tool": "onebase_list_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "onebase_read_config_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_config\""
]
}
},
{
"tool": "onebase_describe_config",
"tags": [],
"reasons": {}
},
{
"tool": "onebase_check_config",
"tags": [],
"reasons": {}
},
{
"tool": "onebase_rest_get",
"tags": [],
"reasons": {}
},
{
"tool": "onebase_rest_write_prepare",
"tags": [],
"reasons": {}
},
{
"tool": "onebase_rest_write_execute",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "283d1b4ec354fb90993a3504a49f049a65b45ba01f336c8a21e7471f853af7bc",
"stats": {
"tools": 47,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 0,
"low": 1,
"info": 0
}
}
}