Onda — 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": "@mindfullabai/onda-mcp",
"source": {
"kind": "package",
"origin": "@mindfullabai/onda-mcp"
},
"server": {
"name": "@mindfullabai/onda-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 1.2,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SUP-010",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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 (43 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 \"onda_pane_split\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_pane_split\" appears to run shell commands or evaluate code (parameter \"shell\"). 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": "onda_pane_split"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"onda_terminal_run\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_terminal_run\" appears to run shell commands or evaluate code (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": "onda_terminal_run"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"onda_tab_new\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_tab_new\" appears to run shell commands or evaluate code (parameter \"shell\"). 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": "onda_tab_new"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"onda_tab_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_tab_exec\" appears to run shell commands or evaluate code (keyword \"exec\" 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": "onda_tab_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"onda_workspace_add_terminal\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_workspace_add_terminal\" appears to run shell commands or evaluate code (parameter \"shell\"). 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": "onda_workspace_add_terminal"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"onda_terminal_spawn\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_terminal_spawn\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "onda_terminal_spawn"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"onda_agent_spawn\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"onda_agent_spawn\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "onda_agent_spawn"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/install-skill.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/install-skill.mjs: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": "bin/install-skill.mjs"
},
"evidence": "spawnSync } from 'node:child_process'; const __dirname = dirname(fileURLToPath(import.meta.url)); const target = resol",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/install-skill.mjs",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:384`): 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/index.js"
},
"evidence": "TH-resolvable binary to spawn (e.g., \"claude\", \"/usr/local/bin/aider\").' }, args: {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 384,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"shell\" on \"onda_pane_split\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"onda_pane_split\" takes a command-shaped parameter \"shell\" 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": "onda_pane_split",
"field": "inputSchema.properties.shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "shell"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"onda_terminal_run\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"onda_terminal_run\" 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": "onda_terminal_run",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"shell\" on \"onda_tab_new\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"onda_tab_new\" takes a command-shaped parameter \"shell\" 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": "onda_tab_new",
"field": "inputSchema.properties.shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "shell"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"shell\" on \"onda_workspace_add_terminal\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"onda_workspace_add_terminal\" takes a command-shaped parameter \"shell\" 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": "onda_workspace_add_terminal",
"field": "inputSchema.properties.shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "shell"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_pane_split\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_pane_split\" 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": "onda_pane_split"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_terminal_run\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_terminal_run\" 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": "onda_terminal_run"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_tab_new\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_tab_new\" 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": "onda_tab_new"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_tab_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_tab_exec\" 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": "onda_tab_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_workspace_add_terminal\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_workspace_add_terminal\" 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": "onda_workspace_add_terminal"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_terminal_spawn\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_terminal_spawn\" 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": "onda_terminal_spawn"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"onda_agent_spawn\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"onda_agent_spawn\" 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": "onda_agent_spawn"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-010",
"title": "Package runs install-time scripts (postinstall)",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"description": "\"@mindfullabai/onda-mcp\" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.",
"remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
"location": {
"kind": "package",
"name": "@mindfullabai/onda-mcp"
},
"evidence": "node scripts/install-skill.mjs --quiet || true",
"owasp": "LLM03:2025 Supply Chain",
"references": [
"https://github.com/ossf/package-analysis",
"https://owasp.org/www-project-top-10-ci-cd-security-risks/"
],
"data": {
"scripts": [
"postinstall"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "onda_pane_split",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"shell\""
]
}
},
{
"tool": "onda_pane_list",
"tags": [],
"reasons": {}
},
{
"tool": "onda_pane_close",
"tags": [],
"reasons": {}
},
{
"tool": "onda_pane_focus",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_run",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"command\""
]
}
},
{
"tool": "onda_terminal_send",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_list",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_kill",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_read",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_subscribe",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_poll",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_unsubscribe",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_listeners",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "onda_workspace_layout",
"tags": [],
"reasons": {}
},
{
"tool": "onda_window_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_send_keys",
"tags": [],
"reasons": {}
},
{
"tool": "onda_tab_new",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"shell\""
]
}
},
{
"tool": "onda_tab_list",
"tags": [],
"reasons": {}
},
{
"tool": "onda_tab_close",
"tags": [],
"reasons": {}
},
{
"tool": "onda_tab_focus",
"tags": [],
"reasons": {}
},
{
"tool": "onda_tab_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "onda_workspace_list",
"tags": [],
"reasons": {}
},
{
"tool": "onda_workspace_create",
"tags": [],
"reasons": {}
},
{
"tool": "onda_workspace_focus",
"tags": [],
"reasons": {}
},
{
"tool": "onda_workspace_add_terminal",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"shell\""
]
}
},
{
"tool": "onda_workspace_tile",
"tags": [],
"reasons": {}
},
{
"tool": "onda_workspace_locate",
"tags": [],
"reasons": {}
},
{
"tool": "onda_window_list",
"tags": [],
"reasons": {}
},
{
"tool": "onda_window_new",
"tags": [],
"reasons": {}
},
{
"tool": "onda_window_focus",
"tags": [],
"reasons": {}
},
{
"tool": "onda_window_mount_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "onda_workspace_unmount",
"tags": [],
"reasons": {}
},
{
"tool": "onda_terminal_spawn",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "onda_launch_session",
"tags": [],
"reasons": {}
},
{
"tool": "onda_agent_spawn",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "onda_agent_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "onda_agent_wait",
"tags": [],
"reasons": {}
},
{
"tool": "onda_agent_close",
"tags": [],
"reasons": {}
},
{
"tool": "onda_context",
"tags": [],
"reasons": {}
},
{
"tool": "onda_status",
"tags": [],
"reasons": {}
},
{
"tool": "onda_app_info",
"tags": [],
"reasons": {}
},
{
"tool": "onda_ping",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "3c7d2eaf08b06b6a6557c93f256098f9c9b8ab3b5bc6d70bd20e52f96ef813cd",
"stats": {
"tools": 43,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 4,
"low": 8,
"info": 0
}
}
}