Claude Plugin Kubernetes — 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": "claude-plugin-kubernetes",
"source": {
"kind": "package",
"origin": "claude-plugin-kubernetes"
},
"server": {
"name": "claude-plugin-kubernetes"
}
},
"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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"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 (50 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 ([k8s_list_secrets]) and tools that can send data out ([k8s_exec]) 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": "k8s_list_secrets → k8s_exec"
},
"evidence": "sources [k8s_list_secrets] → sinks [k8s_exec]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"k8s_list_secrets"
],
"sinks": [
"k8s_exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"k8s_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"k8s_exec\" appears to run shell commands or evaluate code (keyword \"exec\" in tool name, parameter \"command\"). 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": "k8s_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"k8s_exec\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"k8s_exec\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "k8s_exec",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"k8s_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"k8s_exec\" 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": "k8s_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"claude-plugin-kubernetes\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "claude-plugin-kubernetes"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"claude-plugin-kubernetes\" 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": "claude-plugin-kubernetes"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"k8s_list_secrets"
],
"externalSink": [
"k8s_exec"
],
"selfContained": false,
"path": [
"k8s_list_secrets",
"k8s_exec"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: k8s_list_secrets → k8s_exec."
}
],
"capabilities": [
{
"tool": "k8s_cluster_info",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_get_contexts",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_namespaces",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_pods",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_deployments",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_services",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_images",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_events",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_statefulsets",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_ingresses",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_cronjobs",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_configmaps",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_secrets",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_secrets\""
]
}
},
{
"tool": "k8s_list_pvcs",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_daemonsets",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_hpa",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_networkpolicies",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_api_resources",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_serviceaccounts",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_roles",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_rolebindings",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_pvs",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_storageclasses",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_resourcequotas",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_limitranges",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_list_poddisruptionbudgets",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_get",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_get_configmap_data",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_describe",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_logs",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_top_pods",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_top_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_find_issues",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_get_yaml",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name",
"parameter \"command\""
]
}
},
{
"tool": "k8s_logs_selector",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_self_test",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_rollout_status",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_rollout_history",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_restart_deployment",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_scale",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_delete_pod",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_rollback_deployment",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_apply_manifest",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_patch_resource",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_node_operation",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_delete_resource",
"tags": [],
"reasons": {}
},
{
"tool": "k8s_diff",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b5c08db775fdd84631d05053059ea18943714638b6c2259bc5fda8603a0c1417",
"stats": {
"tools": 50,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 1,
"low": 1,
"info": 2
}
}
}