Exteragram — 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": "@catalystdev/exteragram-mcp",
"source": {
"kind": "package",
"origin": "@catalystdev/exteragram-mcp"
},
"server": {
"name": "@catalystdev/exteragram-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 send data / act on an external service",
"can create, modify or delete files",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec",
"external-sink",
"file-write"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (81 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-FLOW-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([adb_get_logs, generate_read_file]) and tools that can send data out ([adb_shell, generate_send_message, generate_send_message_hook]) are exposed together. An agent can move private data to the sink.",
"remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
"location": {
"kind": "flow",
"name": "adb_get_logs → adb_shell"
},
"evidence": "sources [adb_get_logs, generate_read_file] → sinks [adb_shell, generate_send_message, generate_send_message_hook]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"adb_get_logs",
"generate_read_file"
],
"sinks": [
"adb_shell",
"generate_send_message",
"generate_send_message_hook"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"adb_shell\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"adb_shell\" appears to run shell commands or evaluate code (keyword \"shell\" in tool name, parameter \"command\"). 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": "adb_shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/adb.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/adb.js:14`): 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": "dist/tools/adb.js"
},
"evidence": "port { execSync } from \"child_process\"; import { z } from \"zod\"; import { getPluginContext } from \"../state/plugin-conte",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/adb.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"generate_write_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"generate_write_file\" can write, overwrite or delete files (keyword \"write_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "generate_write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"generate_delete_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"generate_delete_file\" can write, overwrite or delete files (keyword \"delete_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "generate_delete_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"adb_shell\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"adb_shell\" takes a command-shaped parameter \"command\" 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": "adb_shell",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"adb_shell\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"adb_shell\" 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": "adb_shell"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"generate_write_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_write_file\" 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": "generate_write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"generate_delete_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_delete_file\" 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": "generate_delete_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path_expr\" on \"generate_read_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_read_file\" takes a path parameter \"path_expr\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "generate_read_file",
"field": "inputSchema.properties.path_expr"
},
"data": {
"param": "path_expr"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path_expr\" on \"generate_write_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_write_file\" takes a path parameter \"path_expr\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "generate_write_file",
"field": "inputSchema.properties.path_expr"
},
"data": {
"param": "path_expr"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"ensure_dir\" on \"generate_write_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_write_file\" takes a path parameter \"ensure_dir\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "generate_write_file",
"field": "inputSchema.properties.ensure_dir"
},
"data": {
"param": "ensure_dir"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path_expr\" on \"generate_delete_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"generate_delete_file\" takes a path parameter \"path_expr\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "generate_delete_file",
"field": "inputSchema.properties.path_expr"
},
"data": {
"param": "path_expr"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"adb_get_logs",
"generate_read_file"
],
"externalSink": [
"adb_shell",
"generate_send_message",
"generate_send_message_hook"
],
"selfContained": false,
"path": [
"adb_get_logs",
"adb_shell"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: adb_get_logs → adb_shell."
}
],
"capabilities": [
{
"tool": "adb_check_devices",
"tags": [],
"reasons": {}
},
{
"tool": "adb_deploy_plugin",
"tags": [],
"reasons": {}
},
{
"tool": "adb_list_plugins",
"tags": [],
"reasons": {}
},
{
"tool": "adb_remove_plugin",
"tags": [],
"reasons": {}
},
{
"tool": "adb_get_logs",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_logs\""
]
}
},
{
"tool": "adb_restart_app",
"tags": [],
"reasons": {}
},
{
"tool": "adb_push_file",
"tags": [],
"reasons": {}
},
{
"tool": "adb_pull_file",
"tags": [],
"reasons": {}
},
{
"tool": "adb_shell",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\" in tool name",
"parameter \"command\""
]
}
},
{
"tool": "generate_alert_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "generate_ui_thread_call",
"tags": [],
"reasons": {}
},
{
"tool": "generate_click_listener",
"tags": [],
"reasons": {}
},
{
"tool": "generate_runnable",
"tags": [],
"reasons": {}
},
{
"tool": "generate_clipboard_copy",
"tags": [],
"reasons": {}
},
{
"tool": "generate_log",
"tags": [],
"reasons": {}
},
{
"tool": "generate_bulletin",
"tags": [],
"reasons": {}
},
{
"tool": "generate_java_subclass",
"tags": [],
"reasons": {}
},
{
"tool": "generate_joverride",
"tags": [],
"reasons": {}
},
{
"tool": "generate_jfield",
"tags": [],
"reasons": {}
},
{
"tool": "generate_jmvel_method",
"tags": [],
"reasons": {}
},
{
"tool": "generate_java_helper",
"tags": [],
"reasons": {}
},
{
"tool": "generate_new_instance",
"tags": [],
"reasons": {}
},
{
"tool": "generate_from_java",
"tags": [],
"reasons": {}
},
{
"tool": "generate_pyobj",
"tags": [],
"reasons": {}
},
{
"tool": "generate_jclassbuilder",
"tags": [],
"reasons": {}
},
{
"tool": "generate_send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "generate_edit_message",
"tags": [],
"reasons": {}
},
{
"tool": "generate_send_request",
"tags": [],
"reasons": {}
},
{
"tool": "generate_notification_listener",
"tags": [],
"reasons": {}
},
{
"tool": "generate_queue_call",
"tags": [],
"reasons": {}
},
{
"tool": "list_controllers",
"tags": [],
"reasons": {}
},
{
"tool": "list_queue_constants",
"tags": [],
"reasons": {}
},
{
"tool": "set_plugin_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_plugin_context",
"tags": [],
"reasons": {}
},
{
"tool": "clear_plugin_context",
"tags": [],
"reasons": {}
},
{
"tool": "validate_plugin_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "generate_read_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "generate_write_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"write_file\" in tool name"
]
}
},
{
"tool": "generate_delete_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"delete_file\" in tool name"
]
}
},
{
"tool": "generate_ensure_dir",
"tags": [],
"reasons": {}
},
{
"tool": "generate_list_dir",
"tags": [],
"reasons": {}
},
{
"tool": "list_standard_dirs",
"tags": [],
"reasons": {}
},
{
"tool": "generate_find_class",
"tags": [],
"reasons": {}
},
{
"tool": "generate_get_field",
"tags": [],
"reasons": {}
},
{
"tool": "generate_set_field",
"tags": [],
"reasons": {}
},
{
"tool": "generate_on_plugin_load",
"tags": [],
"reasons": {}
},
{
"tool": "generate_on_plugin_unload",
"tags": [],
"reasons": {}
},
{
"tool": "generate_on_app_event",
"tags": [],
"reasons": {}
},
{
"tool": "generate_menu_item",
"tags": [],
"reasons": {}
},
{
"tool": "generate_send_message_hook",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "generate_hook_result",
"tags": [],
"reasons": {}
},
{
"tool": "list_hook_strategies",
"tags": [],
"reasons": {}
},
{
"tool": "list_app_events",
"tags": [],
"reasons": {}
},
{
"tool": "list_menu_types",
"tags": [],
"reasons": {}
},
{
"tool": "list_settings_components",
"tags": [],
"reasons": {}
},
{
"tool": "list_available_libraries",
"tags": [],
"reasons": {}
},
{
"tool": "list_common_classes",
"tags": [],
"reasons": {}
},
{
"tool": "get_plugin_template",
"tags": [],
"reasons": {}
},
{
"tool": "explain_pitfalls",
"tags": [],
"reasons": {}
},
{
"tool": "list_hook_filters",
"tags": [],
"reasons": {}
},
{
"tool": "generate_pre_request_hook",
"tags": [],
"reasons": {}
},
{
"tool": "generate_post_request_hook",
"tags": [],
"reasons": {}
},
{
"tool": "generate_on_update_hook",
"tags": [],
"reasons": {}
},
{
"tool": "generate_on_updates_hook",
"tags": [],
"reasons": {}
},
{
"tool": "generate_plugin_file",
"tags": [],
"reasons": {}
},
{
"tool": "generate_metadata_block",
"tags": [],
"reasons": {}
},
{
"tool": "generate_import_block",
"tags": [],
"reasons": {}
},
{
"tool": "generate_settings_ui",
"tags": [],
"reasons": {}
},
{
"tool": "generate_settings_component",
"tags": [],
"reasons": {}
},
{
"tool": "generate_get_setting",
"tags": [],
"reasons": {}
},
{
"tool": "generate_set_setting",
"tags": [],
"reasons": {}
},
{
"tool": "generate_export_import_settings",
"tags": [],
"reasons": {}
},
{
"tool": "generate_simple_setting_factory",
"tags": [],
"reasons": {}
},
{
"tool": "generate_parse_text",
"tags": [],
"reasons": {}
},
{
"tool": "list_html_tags",
"tags": [],
"reasons": {}
},
{
"tool": "generate_method_hook",
"tags": [],
"reasons": {}
},
{
"tool": "generate_hook_param_usage",
"tags": [],
"reasons": {}
},
{
"tool": "generate_hook_filters",
"tags": [],
"reasons": {}
},
{
"tool": "generate_hook_all_methods",
"tags": [],
"reasons": {}
},
{
"tool": "generate_hook_all_constructors",
"tags": [],
"reasons": {}
},
{
"tool": "generate_unhook",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c7e2f5706fb289f559e16ea1326817dc47074b51958d2ef4a0de6ae8a82c5fe8",
"stats": {
"tools": 81,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 3,
"low": 7,
"info": 0
}
}
}