Rate-My-Agent — 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://mcp.rate-my-agent.com/mcp",
"source": {
"kind": "http",
"origin": "https://mcp.rate-my-agent.com/mcp"
},
"server": {
"name": "rate-my-agent",
"version": "1.1.1"
}
},
"grade": "F",
"score": {
"score": 47,
"threatScore": 50,
"grade": "F",
"band": "F",
"gateCap": "D",
"categorySubtotals": {
"injection": 50,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-POISON",
"category": "injection",
"severity": "critical",
"confidence": "strong",
"rawWeight": 45,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 31.5
},
{
"kind": "threat",
"ruleId": "MTC-INJ-SECRECY-1",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"kind": "threat",
"ruleId": "MTC-INJ-SECRECY-1",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 7.7
},
{
"kind": "client",
"term": "capability-exposure",
"level": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "live",
"label": "inspection depth (live) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [
"a critical finding is present → grade capped at D"
],
"methodologyVersion": "mcptrustchecker-1.9"
},
"capability": {
"level": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)"
],
"tags": [
"untrusted-input"
]
},
"coverage": {
"level": "live",
"inputs": {
"toolSurface": true,
"implementationSource": false,
"packageMetadata": false,
"liveTransport": true
},
"caveats": []
},
"findings": [
{
"ruleId": "MTC-INJ-POISON",
"title": "Compound tool-poisoning pattern",
"category": "injection",
"severity": "critical",
"confidence": "strong",
"description": "Multiple tool-poisoning signals co-occur in a single field (authority, secrecy), including a concealment / override / sensitive-target directive. Together they form an instruction aimed at the model — the canonical tool-poisoning shape, not ordinary documentation.",
"remediation": "Do not install this server; the metadata is engineered to manipulate the assistant.",
"location": {
"kind": "tool",
"name": "submit_lead",
"field": "description"
},
"evidence": "Submit the completed lead. ONLY call after you have echoed the exact contact details and quiz answers back to the client and they picked the clearly-labeled \"1. Confirm and Submit Request\" option — se",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kinds": [
"authority",
"secrecy"
]
}
},
{
"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": "DO NOT tell the user",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "secrecy"
}
},
{
"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 description of tool \"submit_lead\". 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": "tool",
"name": "submit_lead",
"field": "description"
},
"evidence": "NEVER tell the user",
"owasp": "LLM01:2025 Prompt Injection",
"data": {
"kind": "secrecy"
}
},
{
"ruleId": "MTC-NET-005",
"title": "Remote HTTP MCP endpoint",
"category": "network",
"severity": "info",
"confidence": "strong",
"description": "Remote endpoint mcp.rate-my-agent.com. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
"location": {
"kind": "transport"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "search_agents",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"web_search\""
]
}
},
{
"tool": "get_lead_quiz",
"tags": [],
"reasons": {}
},
{
"tool": "submit_lead",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "256823977e5233a21f129d6023ba78182d12daa8bde68d9b185616d45946e057",
"stats": {
"tools": 3,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 2,
"medium": 0,
"low": 0,
"info": 1
}
}
}