Pandamcp — 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": "pandamcp",
"source": {
"kind": "package",
"origin": "pandamcp"
},
"server": {
"name": "pandamcp"
}
},
"grade": "C",
"score": {
"score": 78,
"threatScore": 85,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 15.4,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-010",
"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": "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-1.8"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (30 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-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/browser/raw-cdp-backend.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/browser/raw-cdp-backend.js:341`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. 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/browser/raw-cdp-backend.js"
},
"evidence": "urn frame.contentWindow.eval(${JSON.stringify(expression)}); } return Function(\"window\", \"document\", \"re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/browser/raw-cdp-backend.js",
"line": 341,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/browser/raw-cdp-backend.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/browser/raw-cdp-backend.js:343`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/browser/raw-cdp-backend.js"
},
"evidence": "} return Function(\"window\", \"document\", \"return (\" + ${JSON.stringify(expression)} + \");\")( fra",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/browser/raw-cdp-backend.js",
"line": 343,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([browser_set_download_behavior]) co-exist with external-action tools ([browser_upload_file]). 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": "browser_set_download_behavior → browser_upload_file"
},
"evidence": "untrusted [browser_set_download_behavior] → sinks [browser_upload_file]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"browser_set_download_behavior"
],
"sinks": [
"browser_upload_file"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"browser_set_download_behavior"
],
"sensitiveSource": [],
"externalSink": [
"browser_upload_file"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "browser_new_page",
"tags": [],
"reasons": {}
},
{
"tool": "browser_list_pages",
"tags": [],
"reasons": {}
},
{
"tool": "browser_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "browser_text",
"tags": [],
"reasons": {}
},
{
"tool": "browser_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "browser_wait_for_text",
"tags": [],
"reasons": {}
},
{
"tool": "browser_wait_for_selector",
"tags": [],
"reasons": {}
},
{
"tool": "browser_wait_for_url",
"tags": [],
"reasons": {}
},
{
"tool": "browser_wait_for_load_state",
"tags": [],
"reasons": {}
},
{
"tool": "browser_wait_for_expression",
"tags": [],
"reasons": {}
},
{
"tool": "browser_fill",
"tags": [],
"reasons": {}
},
{
"tool": "browser_press",
"tags": [],
"reasons": {}
},
{
"tool": "browser_select_option",
"tags": [],
"reasons": {}
},
{
"tool": "browser_drag_and_drop",
"tags": [],
"reasons": {}
},
{
"tool": "browser_upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "browser_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "browser_response_body",
"tags": [],
"reasons": {}
},
{
"tool": "browser_set_cookie",
"tags": [],
"reasons": {}
},
{
"tool": "browser_storage",
"tags": [],
"reasons": {}
},
{
"tool": "browser_set_storage",
"tags": [],
"reasons": {}
},
{
"tool": "browser_clear_storage",
"tags": [],
"reasons": {}
},
{
"tool": "browser_grant_permissions",
"tags": [],
"reasons": {}
},
{
"tool": "browser_set_geolocation",
"tags": [],
"reasons": {}
},
{
"tool": "browser_frame_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "browser_create_context",
"tags": [],
"reasons": {}
},
{
"tool": "browser_list_contexts",
"tags": [],
"reasons": {}
},
{
"tool": "browser_close_context",
"tags": [],
"reasons": {}
},
{
"tool": "browser_set_download_behavior",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "browser_set_blocked_urls",
"tags": [],
"reasons": {}
},
{
"tool": "browser_close_browser",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "645895cbd706eb00e512042640548d66d0e98c391d5a2f949e0aa19d6bfb8f31",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 1,
"low": 0,
"info": 0
}
}
}