Babeltower Agent — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "babeltower-agent",
"source": {
"kind": "package",
"origin": "babeltower-agent"
},
"server": {
"name": "babeltower-agent"
}
},
"grade": "A",
"score": {
"score": 95,
"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": "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-1.8"
},
"capability": {
"level": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service"
],
"tags": [
"untrusted-input",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (25 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 ([get_intent, session_read_messages]) co-exist with external-action tools ([session_send_message]). 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": "get_intent → session_send_message"
},
"evidence": "untrusted [get_intent, session_read_messages] → sinks [session_send_message]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"get_intent",
"session_read_messages"
],
"sinks": [
"session_send_message"
]
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"babeltower-agent\" 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": "babeltower-agent"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"get_intent",
"session_read_messages"
],
"sensitiveSource": [],
"externalSink": [
"session_send_message"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "my_identity",
"tags": [],
"reasons": {}
},
{
"tool": "server_info",
"tags": [],
"reasons": {}
},
{
"tool": "register_init",
"tags": [],
"reasons": {}
},
{
"tool": "register_status",
"tags": [],
"reasons": {}
},
{
"tool": "post_intent",
"tags": [],
"reasons": {}
},
{
"tool": "get_intent",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "list_my_intents",
"tags": [],
"reasons": {}
},
{
"tool": "delete_intent",
"tags": [],
"reasons": {}
},
{
"tool": "refresh_intent",
"tags": [],
"reasons": {}
},
{
"tool": "search",
"tags": [],
"reasons": {}
},
{
"tool": "send_connect",
"tags": [],
"reasons": {}
},
{
"tool": "get_inbox",
"tags": [],
"reasons": {}
},
{
"tool": "session_list",
"tags": [],
"reasons": {}
},
{
"tool": "session_read_messages",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_message\""
]
}
},
{
"tool": "session_send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "session_send_handoff",
"tags": [],
"reasons": {}
},
{
"tool": "session_end",
"tags": [],
"reasons": {}
},
{
"tool": "handoff_list",
"tags": [],
"reasons": {}
},
{
"tool": "accept_connect",
"tags": [],
"reasons": {}
},
{
"tool": "reject_connect",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_connect",
"tags": [],
"reasons": {}
},
{
"tool": "propose_match",
"tags": [],
"reasons": {}
},
{
"tool": "accept_match",
"tags": [],
"reasons": {}
},
{
"tool": "reject_match",
"tags": [],
"reasons": {}
},
{
"tool": "end_session",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "6b92e8b281c7d357dfab4522494e43bd022e794322a14a594317a47c61e02007",
"stats": {
"tools": 25,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 1,
"low": 0,
"info": 1
}
}
}