Browser Lens — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "browser-lens-mcp",
"source": {
"kind": "package",
"origin": "browser-lens-mcp"
},
"server": {
"name": "browser-lens-mcp"
}
},
"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-1.13"
},
"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": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (31 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 (extension/background.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`extension/background.js:64`): 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": "extension/background.js"
},
"evidence": "try { new Function(code).call(window); } catch (e) { console.error(\"[BrowserLens Ext",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "extension/background.js",
"line": 64,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/src/transport/connector-script.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/src/transport/connector-script.js:280`): 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/src/transport/connector-script.js"
},
"evidence": "g html2canvas via fetch+eval (CSP-safe)...'); fetch(HTTP_URL.replace('/ingest','/html2canvas.js')).then(function(r){",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/src/transport/connector-script.js",
"line": 280,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (extension/background.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`extension/background.js:64`): 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": "extension/background.js"
},
"evidence": "try { new Function(code).call(window); } catch (e) { console.error(\"[BrowserLens Ext",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "extension/background.js",
"line": 64,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_page_info",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_dom_tree",
"tags": [],
"reasons": {}
},
{
"tool": "inspect_element",
"tags": [],
"reasons": {}
},
{
"tool": "query_selector",
"tags": [],
"reasons": {}
},
{
"tool": "get_computed_styles",
"tags": [],
"reasons": {}
},
{
"tool": "get_layout_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_page_screenshot",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_all_screenshots",
"tags": [],
"reasons": {}
},
{
"tool": "get_css_variables",
"tags": [],
"reasons": {}
},
{
"tool": "get_typography",
"tags": [],
"reasons": {}
},
{
"tool": "get_color_palette",
"tags": [],
"reasons": {}
},
{
"tool": "get_accessibility_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_responsive_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_spacing_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "get_dom_mutations",
"tags": [],
"reasons": {}
},
{
"tool": "compare_with_figma",
"tags": [],
"reasons": {}
},
{
"tool": "get_comparison_history",
"tags": [],
"reasons": {}
},
{
"tool": "describe_ui",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_css_fixes",
"tags": [],
"reasons": {}
},
{
"tool": "get_element_hierarchy",
"tags": [],
"reasons": {}
},
{
"tool": "get_elements_summary",
"tags": [],
"reasons": {}
},
{
"tool": "clear_data",
"tags": [],
"reasons": {}
},
{
"tool": "get_connection_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_full_page_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "get_design_tokens",
"tags": [],
"reasons": {}
},
{
"tool": "get_visual_diff_report",
"tags": [],
"reasons": {}
},
{
"tool": "capture_screenshot_with_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "inspect_feature_area",
"tags": [],
"reasons": {}
},
{
"tool": "trigger_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "live_query_element",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot_element",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "3d50276e96fddfc77748ad20da9f4cf35d22e5de9d602a28f6d1556b8c3e4e19",
"stats": {
"tools": 31,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 0,
"low": 0,
"info": 0
}
}
}