Pbi Webview2 — 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": "pbi-webview2",
"source": {
"kind": "package",
"origin": "pbi-webview2"
},
"server": {
"name": "pbi-webview2"
}
},
"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": [
"code-exec",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (55 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-CAP-001",
"title": "Tool \"pbi_eval\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"pbi_eval\" appears to run shell commands or evaluate code (keyword \"eval\" 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": "pbi_eval"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"pbi_run_code\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"pbi_run_code\" appears to run shell commands or evaluate code (keyword \"run_code\" 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": "pbi_run_code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/tools.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools.js:1141`): 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": "src/tools.js"
},
"evidence": "const fn = eval('(' + code + ')'); return typeof fn === 'function' ? fn() : fn; }",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/tools.js",
"line": 1141,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/launch.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/launch.js:9`): 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": "src/launch.js"
},
"evidence": "spawnSync } from 'node:child_process'; import fs from 'node:fs'; import path from 'node:path'; const CDP_HOST = '127.0",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/launch.js",
"line": 9,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([pbi_drill]) co-exist with external-action tools ([pbi_eval, pbi_run_code]). 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": "pbi_drill → pbi_eval"
},
"evidence": "untrusted [pbi_drill] → sinks [pbi_eval, pbi_run_code]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"pbi_drill"
],
"sinks": [
"pbi_eval",
"pbi_run_code"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"code\" on \"pbi_run_code\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"pbi_run_code\" 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": "pbi_run_code",
"field": "inputSchema.properties.code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "code"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"pbi_eval\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"pbi_eval\" 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": "pbi_eval"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"pbi_run_code\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"pbi_run_code\" 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": "pbi_run_code"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"pbi_drill"
],
"sensitiveSource": [],
"externalSink": [
"pbi_eval",
"pbi_run_code"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "pbi_launch",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_status",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_pages",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_goto_page",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_deselect",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_state_probe",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_cards",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_click",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_set_slicer",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_fire_bookmark",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_matrix",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_matrix_expand",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_cross_filter_test",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_hover_tooltip",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_scan_errors",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_perf_analyzer",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_page_sweep",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_baseline",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_eval",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "pbi_run_code",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_code\" in tool name"
]
}
},
{
"tool": "pbi_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_type",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_search_slicer",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_context_menu",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_visuals",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_dax_editor",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_tmdl",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_dax_query",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_editor_buffer",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_model_info",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_dax_batch",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_format_dax",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_table",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_show_as_table",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_slicer",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_read_filters",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_expand_all",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_sort_column",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_multiselect_slicer",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_drill",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "pbi_keyboard_nav",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_page_digest",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_diff_state",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_assert",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_annotate_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_deep_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_emulate_theme",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_save",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_close",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_reload",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_health",
"tags": [],
"reasons": {}
},
{
"tool": "pbi_wait_stable",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "a92ddd08c964b7c0c494ec3173b92be42123671149d4d6406c858d2a399ca993",
"stats": {
"tools": 55,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 2,
"low": 2,
"info": 0
}
}
}