Pathlight — 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": "pathlight-mcp",
"source": {
"kind": "package",
"origin": "pathlight-mcp"
},
"server": {
"name": "pathlight-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-1.8"
},
"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": [
"external-sink",
"sensitive-source",
"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-006",
"title": "Reads a sensitive credential path or dumps the environment (tests/harness/server.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/harness/server.py:77`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "tests/harness/server.py"
},
"evidence": "dict(os.environ)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/harness/server.py",
"line": 77
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pathlight_mcp/backends/linux.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pathlight_mcp/backends/linux.py:1686`): 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/pathlight_mcp/backends/linux.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pathlight_mcp/backends/linux.py",
"line": 1686
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/pathlight_mcp/cdp/browser_resolver.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/pathlight_mcp/cdp/browser_resolver.py:221`): 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/pathlight_mcp/cdp/browser_resolver.py"
},
"evidence": "subprocess.Popen(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pathlight_mcp/cdp/browser_resolver.py",
"line": 221
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/verify_release.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify_release.py:100`): 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": "scripts/verify_release.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/verify_release.py",
"line": 100
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (src/pathlight_mcp/tools/launch_app.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/pathlight_mcp/tools/launch_app.py:136`): 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/pathlight_mcp/tools/launch_app.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/pathlight_mcp/tools/launch_app.py",
"line": 136
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/fixtures/capture_linux_snapshots.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/fixtures/capture_linux_snapshots.py:83`): 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": "tests/fixtures/capture_linux_snapshots.py"
},
"evidence": "subprocess.Popen(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/fixtures/capture_linux_snapshots.py",
"line": 83
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/fixtures/capture_windows_snapshots.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/fixtures/capture_windows_snapshots.py:91`): 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": "tests/fixtures/capture_windows_snapshots.py"
},
"evidence": "subprocess.Popen(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/fixtures/capture_windows_snapshots.py",
"line": 91
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "desktop.click",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.clipboard_read",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.clipboard_write",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.find",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.focus_window",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.get_table_info",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.get_text",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.get_tree_info",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.launch_app",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.list_windows",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.manage_window",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.multi_action",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.press_key",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.scroll_to_item",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.type_text",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_click",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_connect",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_frame_tree",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_hover",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_list_tabs",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_select_option",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_tab_action",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_type",
"tags": [],
"reasons": {}
},
{
"tool": "desktop.web_upload_files",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "desktop.web_wait_for",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "088a96c23bf1a3982fa99baca153a179cf5141400d42c2b686719e9a484b9e20",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 0,
"low": 4,
"info": 0
}
}
}