Charles — 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": "charles-mcp",
"source": {
"kind": "package",
"origin": "charles-mcp"
},
"server": {
"name": "charles-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": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (34 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-002",
"title": "Shell/command execution in server code (charles_mcp/reverse/ingest/native_convert.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`charles_mcp/reverse/ingest/native_convert.py:23`): 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": "charles_mcp/reverse/ingest/native_convert.py"
},
"evidence": "r(target)] result = subprocess.run( command, capture_output=True, text=True, check=F",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "charles_mcp/reverse/ingest/native_convert.py",
"line": 23,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (charles_mcp/live_state.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`charles_mcp/live_state.py:87`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "charles_mcp/live_state.py"
},
"evidence": "capture = self.require(capture_id) capture.status = \"stopped\" self.active = None return",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "charles_mcp/live_state.py",
"line": 87,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (charles_mcp/services/live_capture.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`charles_mcp/services/live_capture.py:115`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "charles_mcp/services/live_capture.py"
},
"evidence": "ure = self.live_manager.require(capture_id) raw_items = await self.export_current_session() self.live_ma",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "charles_mcp/services/live_capture.py",
"line": 115,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"charles-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "charles-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "reverse_import_session",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_list_captures",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_query_entries",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_get_entry_detail",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_decode_entry_body",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_replay_entry",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_discover_signature_candidates",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_list_findings",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_charles_recording_status",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_start_live_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_peek_live_entries",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_read_live_entries",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_stop_live_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_analyze_live_login_flow",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_analyze_live_api_flow",
"tags": [],
"reasons": {}
},
{
"tool": "reverse_analyze_live_signature_flow",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_recorded_traffic",
"tags": [],
"reasons": {}
},
{
"tool": "get_traffic_entry_detail",
"tags": [],
"reasons": {}
},
{
"tool": "get_capture_analysis_stats",
"tags": [],
"reasons": {}
},
{
"tool": "group_capture_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "query_recorded_traffic",
"tags": [],
"reasons": {}
},
{
"tool": "list_recordings",
"tags": [],
"reasons": {}
},
{
"tool": "get_recording_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_by_time",
"tags": [],
"reasons": {}
},
{
"tool": "filter_func",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "start_live_capture",
"tags": [],
"reasons": {}
},
{
"tool": "read_live_capture",
"tags": [],
"reasons": {}
},
{
"tool": "peek_live_capture",
"tags": [],
"reasons": {}
},
{
"tool": "stop_live_capture",
"tags": [],
"reasons": {}
},
{
"tool": "query_live_capture_entries",
"tags": [],
"reasons": {}
},
{
"tool": "throttling",
"tags": [],
"reasons": {}
},
{
"tool": "reset_environment",
"tags": [],
"reasons": {}
},
{
"tool": "charles_status",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "bc1f102016ab044e0634ec306ad4041f34b2426ef5c40c306520ac3e5610d566",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 2,
"low": 0,
"info": 1
}
}
}