Gravitykit — 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": "@gravitykit/mcp",
"source": {
"kind": "package",
"origin": "@gravitykit/mcp"
},
"server": {
"name": "@gravitykit/mcp"
}
},
"grade": "A",
"score": {
"score": 97,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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 (23 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 ([gk_reload_abilities]) co-exist with external-action tools ([gf_send_notifications]). 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": "gk_reload_abilities → gf_send_notifications"
},
"evidence": "untrusted [gk_reload_abilities] → sinks [gf_send_notifications]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"gk_reload_abilities"
],
"sinks": [
"gf_send_notifications"
]
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (src/field-definitions/loader.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/field-definitions/loader.js:129`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/field-definitions/loader.js"
},
"evidence": "const module = await import(distPath); const { fieldRegistry } = module; if (fieldRegistry && fiel",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/field-definitions/loader.js",
"line": 129,
"nonRuntime": false
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"gk_reload_abilities"
],
"sensitiveSource": [],
"externalSink": [
"gf_send_notifications"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "gf_list_forms",
"tags": [],
"reasons": {}
},
{
"tool": "gf_get_form",
"tags": [],
"reasons": {}
},
{
"tool": "gf_create_form",
"tags": [],
"reasons": {}
},
{
"tool": "gf_update_form",
"tags": [],
"reasons": {}
},
{
"tool": "gf_delete_form",
"tags": [],
"reasons": {}
},
{
"tool": "gf_validate_form",
"tags": [],
"reasons": {}
},
{
"tool": "gf_list_entries",
"tags": [],
"reasons": {}
},
{
"tool": "gf_get_entry",
"tags": [],
"reasons": {}
},
{
"tool": "gf_create_entry",
"tags": [],
"reasons": {}
},
{
"tool": "gf_update_entry",
"tags": [],
"reasons": {}
},
{
"tool": "gf_delete_entry",
"tags": [],
"reasons": {}
},
{
"tool": "gf_submit_form_data",
"tags": [],
"reasons": {}
},
{
"tool": "gf_validate_submission",
"tags": [],
"reasons": {}
},
{
"tool": "gf_send_notifications",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_notification\""
]
}
},
{
"tool": "gf_list_feeds",
"tags": [],
"reasons": {}
},
{
"tool": "gf_get_feed",
"tags": [],
"reasons": {}
},
{
"tool": "gf_create_feed",
"tags": [],
"reasons": {}
},
{
"tool": "gf_update_feed",
"tags": [],
"reasons": {}
},
{
"tool": "gf_patch_feed",
"tags": [],
"reasons": {}
},
{
"tool": "gf_delete_feed",
"tags": [],
"reasons": {}
},
{
"tool": "gf_get_field_filters",
"tags": [],
"reasons": {}
},
{
"tool": "gf_get_results",
"tags": [],
"reasons": {}
},
{
"tool": "gk_reload_abilities",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
}
],
"surfaceDigest": "4cc3c29e1d65f2d3736e34472443237892040f8d6c0b8854de0309097add8e4d",
"stats": {
"tools": 23,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 2,
"low": 0,
"info": 0
}
}
}