Vaaya — the complete, unedited output of the deterministic mcptrustchecker engine v1.10.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.10.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "https://vaaya.ai/mcp",
"source": {
"kind": "http",
"origin": "https://vaaya.ai/mcp"
},
"server": {
"name": "vaaya",
"version": "1.0.0"
}
},
"grade": "C",
"score": {
"score": 72,
"threatScore": 78,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 15.4,
"exfiltration": 0,
"permissions": 6.3,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-CAP-003",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-INJ-SECRECY-1",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "live",
"label": "inspection depth (live) — 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": "live",
"inputs": {
"toolSurface": true,
"implementationSource": false,
"packageMetadata": false,
"liveTransport": true
},
"caveats": []
},
"findings": [
{
"ruleId": "MTC-INJ-SECRECY-1",
"title": "Secrecy directive (conceal action from the user)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "Secrecy directive (conceal action from the user) detected in the instructions of server. Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.",
"remediation": "Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.",
"location": {
"kind": "server",
"field": "instructions"
},
"evidence": "Never tell the user",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "secrecy"
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"session\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"session\" appears to run shell commands or evaluate code (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": "session"
},
"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 ([consult, use, result]) co-exist with external-action tools ([session]). 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": "consult → session"
},
"evidence": "untrusted [consult, use, result] → sinks [session]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"consult",
"use",
"result"
],
"sinks": [
"session"
]
}
},
{
"ruleId": "MTC-CAP-003",
"title": "Annotation contradicts behavior on \"session\"",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"session\" advertises destructiveHint=false but its derived capabilities include state-modifying actions (code-exec). Tool annotations are attacker-controllable and must never be trusted; a mismatch like this is exactly how a hostile server hides a destructive tool.",
"remediation": "Ignore server-provided annotations for security decisions; gate destructive tools on explicit user consent.",
"location": {
"kind": "tool",
"name": "session"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"tags": [
"code-exec"
],
"annotations": {
"title": "Run Code in a Sandbox Session",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"session\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"session\" 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": "session",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"code\" on \"session\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"session\" takes a command-shaped parameter \"code\" 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": "session",
"field": "inputSchema.properties.code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "code"
}
},
{
"ruleId": "MTC-NET-005",
"title": "Remote HTTP MCP endpoint",
"category": "network",
"severity": "info",
"confidence": "strong",
"description": "Remote endpoint vaaya.ai. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
"location": {
"kind": "transport"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"consult",
"use",
"result"
],
"sensitiveSource": [],
"externalSink": [
"session"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "vaaya_test_connection",
"tags": [],
"reasons": {}
},
{
"tool": "vaaya_onboard",
"tags": [],
"reasons": {}
},
{
"tool": "vaaya_account",
"tags": [],
"reasons": {}
},
{
"tool": "vaaya_logout",
"tags": [],
"reasons": {}
},
{
"tool": "consult",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "use",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"web_search\""
]
}
},
{
"tool": "result",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "session",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "close",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b067f71b37d910d5b82a130523d3ac118bcf956689dc1eb8600e416d205ccece",
"stats": {
"tools": 9,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 4,
"low": 0,
"info": 1
}
}
}