Solana Clawd — the complete, unedited output of the deterministic mcptrustchecker engine v1.12.1, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.12.1",
"methodologyVersion": "mcptrustchecker-1.12"
},
"target": {
"id": "solana-clawd",
"source": {
"kind": "package",
"origin": "solana-clawd"
},
"server": {
"name": "solana-clawd"
}
},
"grade": "A",
"score": {
"score": 93,
"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": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"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-1.12"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"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",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (59 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 ([solana_token_info]) and tools that can send data out ([agent_spawn, helius_webhook_create]) 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": "solana_token_info → agent_spawn"
},
"evidence": "sources [solana_token_info] → sinks [agent_spawn, helius_webhook_create]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"solana_token_info"
],
"sinks": [
"agent_spawn",
"helius_webhook_create"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"agent_spawn\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"agent_spawn\" appears to run shell commands or evaluate code (keyword \"spawn\" in tool name). 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": "agent_spawn"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/entrypoints/clawd.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/entrypoints/clawd.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. 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": "dist/entrypoints/clawd.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; const __filename = fileURLToPath(import.meta.url); const __dirname = path.dirnam",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/entrypoints/clawd.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (mcp/dist/server.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`mcp/dist/server.js:39`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "mcp/dist/server.js"
},
"evidence": "{ const res = await fetch(`https://data.solanatracker.io${path}`, { headers: { Accept: \"applicat",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "mcp/dist/server.js",
"line": 39,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (tui/dist/market.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`tui/dist/market.js:92`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "tui/dist/market.js"
},
"evidence": ") { const r = await fetch('https://api.coingecko.com/api/v3/simple/price?ids=solana&vs_currencies=usd&include_24hr_c",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tui/dist/market.js",
"line": 92,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"agent_spawn\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"agent_spawn\" 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": "agent_spawn"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"solana_token_info"
],
"externalSink": [
"agent_spawn",
"helius_webhook_create"
],
"selfContained": false,
"path": [
"solana_token_info",
"agent_spawn"
],
"pathWired": true,
"description": "A sensitive-source → external-sink chain exists: solana_token_info ⇒ agent_spawn."
}
],
"capabilities": [
{
"tool": "README",
"tags": [],
"reasons": {}
},
{
"tool": "SOUL.md",
"tags": [],
"reasons": {}
},
{
"tool": "Skills",
"tags": [],
"reasons": {}
},
{
"tool": "Source Tools",
"tags": [],
"reasons": {}
},
{
"tool": "Source file",
"tags": [],
"reasons": {}
},
{
"tool": "solana_price",
"tags": [],
"reasons": {}
},
{
"tool": "solana_trending",
"tags": [],
"reasons": {}
},
{
"tool": "solana_token_info",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_token\""
]
}
},
{
"tool": "solana_wallet_pnl",
"tags": [],
"reasons": {}
},
{
"tool": "solana_search",
"tags": [],
"reasons": {}
},
{
"tool": "solana_top_traders",
"tags": [],
"reasons": {}
},
{
"tool": "solana_wallet_tokens",
"tags": [],
"reasons": {}
},
{
"tool": "agent_spawn",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "agent_list",
"tags": [],
"reasons": {}
},
{
"tool": "agent_stop",
"tags": [],
"reasons": {}
},
{
"tool": "memory_recall",
"tags": [],
"reasons": {}
},
{
"tool": "memory_write",
"tags": [],
"reasons": {}
},
{
"tool": "skill_list",
"tags": [],
"reasons": {}
},
{
"tool": "skill_read",
"tags": [],
"reasons": {}
},
{
"tool": "sol_price",
"tags": [],
"reasons": {}
},
{
"tool": "helius_account_info",
"tags": [],
"reasons": {}
},
{
"tool": "helius_balance",
"tags": [],
"reasons": {}
},
{
"tool": "helius_transactions",
"tags": [],
"reasons": {}
},
{
"tool": "helius_priority_fee",
"tags": [],
"reasons": {}
},
{
"tool": "helius_das_asset",
"tags": [],
"reasons": {}
},
{
"tool": "helius_webhook_create",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "helius_webhook_list",
"tags": [],
"reasons": {}
},
{
"tool": "helius_listener_setup",
"tags": [],
"reasons": {}
},
{
"tool": "x402_status",
"tags": [],
"reasons": {}
},
{
"tool": "x402_payment_history",
"tags": [],
"reasons": {}
},
{
"tool": "dream_status",
"tags": [],
"reasons": {}
},
{
"tool": "dream_run",
"tags": [],
"reasons": {}
},
{
"tool": "session_summary",
"tags": [],
"reasons": {}
},
{
"tool": "prompt_suggestions",
"tags": [],
"reasons": {}
},
{
"tool": "pump_token_scan",
"tags": [],
"reasons": {}
},
{
"tool": "pump_buy_quote",
"tags": [],
"reasons": {}
},
{
"tool": "pump_sell_quote",
"tags": [],
"reasons": {}
},
{
"tool": "pump_graduation",
"tags": [],
"reasons": {}
},
{
"tool": "pump_market_cap",
"tags": [],
"reasons": {}
},
{
"tool": "pump_top_tokens",
"tags": [],
"reasons": {}
},
{
"tool": "pump_new_tokens",
"tags": [],
"reasons": {}
},
{
"tool": "pump_cashback_info",
"tags": [],
"reasons": {}
},
{
"tool": "chess_player",
"tags": [],
"reasons": {}
},
{
"tool": "chess_recent_games",
"tags": [],
"reasons": {}
},
{
"tool": "chess_current_games",
"tags": [],
"reasons": {}
},
{
"tool": "chess_daily_puzzle",
"tags": [],
"reasons": {}
},
{
"tool": "chess_random_puzzle",
"tags": [],
"reasons": {}
},
{
"tool": "chess_leaderboards",
"tags": [],
"reasons": {}
},
{
"tool": "chess_titled_players",
"tags": [],
"reasons": {}
},
{
"tool": "solana_overview",
"tags": [],
"reasons": {}
},
{
"tool": "trade_research",
"tags": [],
"reasons": {}
},
{
"tool": "token",
"tags": [],
"reasons": {}
},
{
"tool": "ooda_loop",
"tags": [],
"reasons": {}
},
{
"tool": "market_scan",
"tags": [],
"reasons": {}
},
{
"tool": "wallet_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "wallet",
"tags": [],
"reasons": {}
},
{
"tool": "pump_scan",
"tags": [],
"reasons": {}
},
{
"tool": "pump_ooda",
"tags": [],
"reasons": {}
},
{
"tool": "mint",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "4b11ec2db2daf75e8a16cf0950038fdb22abafaa972b4b884cdef4eac34cf22a",
"stats": {
"tools": 59,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 2,
"low": 1,
"info": 0
}
}
}