Edgegate — 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": "edgegate-mcp",
"source": {
"kind": "package",
"origin": "edgegate-mcp"
},
"server": {
"name": "edgegate-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (58 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 \"edgegate_list_eval_packs\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"edgegate_list_eval_packs\" 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": "edgegate_list_eval_packs"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"edgegate_create_eval_set\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"edgegate_create_eval_set\" 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": "edgegate_create_eval_set"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"edgegate_list_eval_sets\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"edgegate_list_eval_sets\" 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": "edgegate_list_eval_sets"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"edgegate_update_eval_set\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"edgegate_update_eval_set\" 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": "edgegate_update_eval_set"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"edgegate_publish_eval_set\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"edgegate_publish_eval_set\" 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": "edgegate_publish_eval_set"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"edgegate_new_eval_set_version\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"edgegate_new_eval_set_version\" 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": "edgegate_new_eval_set_version"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([edgegate_export_run_report, edgegate_get_byo_audit]) co-exist with external-action tools ([edgegate_list_eval_packs, edgegate_create_eval_set, edgegate_list_eval_sets, edgegate_update_eval_set, edgegate_publish_eval_set, edgegate_new_eval_set_version]). 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": "edgegate_export_run_report → edgegate_list_eval_packs"
},
"evidence": "untrusted [edgegate_export_run_report, edgegate_get_byo_audit] → sinks [edgegate_list_eval_packs, edgegate_create_eval_set, edgegate_list_eval_sets, edgegate_up",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"edgegate_export_run_report",
"edgegate_get_byo_audit"
],
"sinks": [
"edgegate_list_eval_packs",
"edgegate_create_eval_set",
"edgegate_list_eval_sets",
"edgegate_update_eval_set",
"edgegate_publish_eval_set",
"edgegate_new_eval_set_version"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edgegate_list_eval_packs\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edgegate_list_eval_packs\" 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": "edgegate_list_eval_packs"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edgegate_create_eval_set\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edgegate_create_eval_set\" 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": "edgegate_create_eval_set"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edgegate_list_eval_sets\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edgegate_list_eval_sets\" 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": "edgegate_list_eval_sets"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edgegate_update_eval_set\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edgegate_update_eval_set\" 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": "edgegate_update_eval_set"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edgegate_publish_eval_set\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edgegate_publish_eval_set\" 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": "edgegate_publish_eval_set"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edgegate_new_eval_set_version\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edgegate_new_eval_set_version\" 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": "edgegate_new_eval_set_version"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"edgegate-mcp\" 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": "edgegate-mcp"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"edgegate_export_run_report",
"edgegate_get_byo_audit"
],
"sensitiveSource": [],
"externalSink": [
"edgegate_list_eval_packs",
"edgegate_create_eval_set",
"edgegate_list_eval_sets",
"edgegate_update_eval_set",
"edgegate_publish_eval_set",
"edgegate_new_eval_set_version"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "edgegate_setup_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_create_pipeline",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_run_gate",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_check_status",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_get_report",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_get_audit_report",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_setup_github_action",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_compare_runs",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_export_run_report",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "edgegate_import_huggingface_model",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_predict_npu_coverage",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_list_promptpacks",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_create_promptpack",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_publish_promptpack",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_connect_huggingface",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_get_huggingface_integration",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_disconnect_huggingface",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_connect_qaihub",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_get_qaihub_integration",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_disconnect_qaihub",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_create_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_list_api_keys",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_create_api_key",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_revoke_api_key",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_list_members",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_list_devices",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_list_device_targets",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_run_device_benchmark",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_invite_member",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_change_member_role",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_remove_member",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_setup_byo_storage",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_attach_byo_role",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_register_byo_bucket",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_check_byo_bucket",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_register_byo_artifact",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_disconnect_byo_bucket",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_llm_compile",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_check_llm_compile_status",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_get_byo_audit",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "edgegate_list_eval_packs",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "edgegate_create_eval_set",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "edgegate_list_eval_sets",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "edgegate_update_eval_set",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "edgegate_publish_eval_set",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "edgegate_new_eval_set_version",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "edgegate_capture_reference",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_check_reference_capture_status",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_compile_genie",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_check_genie_compile_status",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_create_bg_run",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_cancel_run",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_rerun_bg",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_setup_bg_github_action",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_export_compliance_report",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_export_field_recorder_report",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_recorder_status",
"tags": [],
"reasons": {}
},
{
"tool": "edgegate_trigger_replay",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8701976f106e6d2f72dcdb8cbaeee183dc6439f99c8707f59192144053c6be31",
"stats": {
"tools": 58,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 1,
"low": 6,
"info": 1
}
}
}