Runwhen Platform — 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": "runwhen-platform-mcp",
"source": {
"kind": "package",
"origin": "runwhen-platform-mcp"
},
"server": {
"name": "runwhen-platform-mcp"
}
},
"grade": "B",
"score": {
"score": 89,
"threatScore": 100,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (45 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 \"run_script\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_script\" appears to run shell commands or evaluate code (keyword \"run_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": "run_script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_script_and_wait\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_script_and_wait\" appears to run shell commands or evaluate code (keyword \"run_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": "run_script_and_wait"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (skills/build-runwhen-task/references/python-sli-template.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`skills/build-runwhen-task/references/python-sli-template.py:16`): 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": "skills/build-runwhen-task/references/python-sli-template.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "skills/build-runwhen-task/references/python-sli-template.py",
"line": 16
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (skills/build-runwhen-task/references/python-task-template.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`skills/build-runwhen-task/references/python-task-template.py:32`): 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": "skills/build-runwhen-task/references/python-task-template.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "skills/build-runwhen-task/references/python-task-template.py",
"line": 32
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([list_skills]) co-exist with external-action tools ([run_script, run_script_and_wait]). 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": "list_skills → run_script"
},
"evidence": "untrusted [list_skills] → sinks [run_script, run_script_and_wait]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"list_skills"
],
"sinks": [
"run_script",
"run_script_and_wait"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_script\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_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": "run_script"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_script_and_wait\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_script_and_wait\" 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": "run_script_and_wait"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_bundled_authoring.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_bundled_authoring.py:112`): 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/test_bundled_authoring.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_bundled_authoring.py",
"line": 112
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"runwhen-platform-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "runwhen-platform-mcp"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"list_skills"
],
"sensitiveSource": [],
"externalSink": [
"run_script",
"run_script_and_wait"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "workspace_chat",
"tags": [],
"reasons": {}
},
{
"tool": "list_workspaces",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_chat_config",
"tags": [],
"reasons": {}
},
{
"tool": "list_chat_rules",
"tags": [],
"reasons": {}
},
{
"tool": "get_chat_rule",
"tags": [],
"reasons": {}
},
{
"tool": "create_chat_rule",
"tags": [],
"reasons": {}
},
{
"tool": "update_chat_rule",
"tags": [],
"reasons": {}
},
{
"tool": "list_chat_commands",
"tags": [],
"reasons": {}
},
{
"tool": "get_chat_command",
"tags": [],
"reasons": {}
},
{
"tool": "create_chat_command",
"tags": [],
"reasons": {}
},
{
"tool": "update_chat_command",
"tags": [],
"reasons": {}
},
{
"tool": "list_assistants",
"tags": [],
"reasons": {}
},
{
"tool": "get_assistant",
"tags": [],
"reasons": {}
},
{
"tool": "create_assistant",
"tags": [],
"reasons": {}
},
{
"tool": "update_assistant",
"tags": [],
"reasons": {}
},
{
"tool": "delete_assistant",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_issues",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_slxs",
"tags": [],
"reasons": {}
},
{
"tool": "get_run_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_config_index",
"tags": [],
"reasons": {}
},
{
"tool": "get_issue_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_slx_runbook",
"tags": [],
"reasons": {}
},
{
"tool": "search_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "list_knowledge_base_articles",
"tags": [],
"reasons": {}
},
{
"tool": "get_knowledge_base_article",
"tags": [],
"reasons": {}
},
{
"tool": "create_knowledge_base_article",
"tags": [],
"reasons": {}
},
{
"tool": "update_knowledge_base_article",
"tags": [],
"reasons": {}
},
{
"tool": "delete_knowledge_base_article",
"tags": [],
"reasons": {}
},
{
"tool": "search_registry",
"tags": [],
"reasons": {}
},
{
"tool": "get_registry_codebundle",
"tags": [],
"reasons": {}
},
{
"tool": "deploy_registry_codebundle",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_context",
"tags": [],
"reasons": {}
},
{
"tool": "list_skills",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "get_skill",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_secrets",
"tags": [],
"reasons": {}
},
{
"tool": "get_workspace_locations",
"tags": [],
"reasons": {}
},
{
"tool": "validate_script",
"tags": [],
"reasons": {}
},
{
"tool": "run_script",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_script\""
]
}
},
{
"tool": "get_run_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_run_output",
"tags": [],
"reasons": {}
},
{
"tool": "run_script_and_wait",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_script\""
]
}
},
{
"tool": "run_slx",
"tags": [],
"reasons": {}
},
{
"tool": "commit_slx",
"tags": [],
"reasons": {}
},
{
"tool": "delete_slx",
"tags": [],
"reasons": {}
},
{
"tool": "render_codecollection_skill",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "20418207ae8570850232676f7d2adf30a8f3568ea7642b6d8db863eb44377f2a",
"stats": {
"tools": 45,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 1,
"low": 3,
"info": 1
}
}
}