Happy Platform — 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": "happy-platform-mcp",
"source": {
"kind": "package",
"origin": "happy-platform-mcp"
},
"server": {
"name": "happy-platform-mcp"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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 (51 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 \"SN-Execute-Background-Script\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"SN-Execute-Background-Script\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "SN-Execute-Background-Script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"SN-Create-Fix-Script\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"SN-Create-Fix-Script\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "SN-Create-Fix-Script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"SN-Create-Workflow\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"SN-Create-Workflow\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "SN-Create-Workflow"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"SN-Create-Activity\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"SN-Create-Activity\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "SN-Create-Activity"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"SN-Create-Transition\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"SN-Create-Transition\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "SN-Create-Transition"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/oauth-authorization-code.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/oauth-authorization-code.js:210`): 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/oauth-authorization-code.js"
},
"evidence": "} = await import('node:child_process'); const opener = process.platform === 'darwin' ? 'open' : process.platform",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/oauth-authorization-code.js",
"line": 210,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([SN-Catalog-Search-Items, SN-Catalog-Get-Categories]) co-exist with external-action tools ([SN-Execute-Background-Script, SN-Create-Fix-Script, SN-Create-Workflow, SN-Create-Activity, SN-Create-Transition]). 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": "SN-Catalog-Search-Items → SN-Execute-Background-Script"
},
"evidence": "untrusted [SN-Catalog-Search-Items, SN-Catalog-Get-Categories] → sinks [SN-Execute-Background-Script, SN-Create-Fix-Script, SN-Create-Workflow, SN-Create-Activi",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"SN-Catalog-Search-Items",
"SN-Catalog-Get-Categories"
],
"sinks": [
"SN-Execute-Background-Script",
"SN-Create-Fix-Script",
"SN-Create-Workflow",
"SN-Create-Activity",
"SN-Create-Transition"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"SN-Execute-Background-Script\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Execute-Background-Script\" takes a command-shaped parameter \"script\" 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": "SN-Execute-Background-Script",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_name\" on \"SN-Create-Fix-Script\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Fix-Script\" takes a command-shaped parameter \"script_name\" 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": "SN-Create-Fix-Script",
"field": "inputSchema.properties.script_name"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_name"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_content\" on \"SN-Create-Fix-Script\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Fix-Script\" takes a command-shaped parameter \"script_content\" 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": "SN-Create-Fix-Script",
"field": "inputSchema.properties.script_content"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_content"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"SN-Create-Workflow\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Workflow\" takes a command-shaped parameter \"script\" 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": "SN-Create-Workflow",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"condition_script\" on \"SN-Create-Workflow\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Workflow\" takes a command-shaped parameter \"condition_script\" 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": "SN-Create-Workflow",
"field": "inputSchema.properties.condition_script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "condition_script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"SN-Create-Activity\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Activity\" takes a command-shaped parameter \"script\" 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": "SN-Create-Activity",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"condition_script\" on \"SN-Create-Transition\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Transition\" takes a command-shaped parameter \"condition_script\" 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": "SN-Create-Transition",
"field": "inputSchema.properties.condition_script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "condition_script"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"SN-Execute-Background-Script\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"SN-Execute-Background-Script\" 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": "SN-Execute-Background-Script"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"SN-Create-Fix-Script\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Fix-Script\" 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": "SN-Create-Fix-Script"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"SN-Create-Workflow\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Workflow\" 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": "SN-Create-Workflow"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"SN-Create-Activity\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Activity\" 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": "SN-Create-Activity"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"SN-Create-Transition\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"SN-Create-Transition\" 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": "SN-Create-Transition"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/verify-package.mjs)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/verify-package.mjs:8`): 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-package.mjs"
},
"evidence": "spawnSync } from 'node:child_process'; import { inspect } from 'node:util'; const root = resolve(dirname(fileURLToPath",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/verify-package.mjs",
"line": 8,
"nonRuntime": true
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"SN-Catalog-Search-Items",
"SN-Catalog-Get-Categories"
],
"sensitiveSource": [],
"externalSink": [
"SN-Execute-Background-Script",
"SN-Create-Fix-Script",
"SN-Create-Workflow",
"SN-Create-Activity",
"SN-Create-Transition"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "SN-Set-Instance",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Get-Current-Instance",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Query-Table",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Create-Record",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Get-Record",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Update-Record",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Get-Table-Schema",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-Available-Tables",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-Incidents",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Create-Incident",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Get-Incident",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-SysUsers",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-CmdbCis",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-SysUserGroups",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-ChangeRequests",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Set-Update-Set",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Get-Current-Update-Set",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-Update-Sets",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Set-Current-Application",
"tags": [],
"reasons": {}
},
{
"tool": "SN-List-Problems",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Natural-Language-Search",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Execute-Background-Script",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "SN-Create-Fix-Script",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "SN-Discover-Table-Schema",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Batch-Create",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Batch-Update",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Explain-Field",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Validate-Configuration",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Inspect-Update-Set",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Create-Workflow",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "SN-Create-Activity",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "SN-Create-Transition",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "SN-Publish-Workflow",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Move-Records-To-Update-Set",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Clone-Update-Set",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Add-Comment",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Add-Work-Notes",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Assign-Incident",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Resolve-Incident",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Close-Incident",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Add-Change-Comment",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Assign-Change",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Approve-Change",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Add-Problem-Comment",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Close-Problem",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Catalog-Get-Item",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Catalog-Search-Items",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "SN-Catalog-Submit",
"tags": [],
"reasons": {}
},
{
"tool": "SN-Catalog-Get-Categories",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "ServiceNow Instance Info",
"tags": [],
"reasons": {}
},
{
"tool": "All ServiceNow Tables",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c4420631ae9fc27d35b233e9734a7a07732869b18a4b6d1370d41741d6681422",
"stats": {
"tools": 51,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 8,
"low": 6,
"info": 0
}
}
}