Opencode — 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": "opencode-mcp",
"source": {
"kind": "package",
"origin": "opencode-mcp"
},
"server": {
"name": "opencode-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",
"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"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (80 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 ([opencode_file_list]) and tools that can send data out ([opencode_shell_execute, opencode_project_init, opencode_tui_execute_command]) 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": "opencode_file_list → opencode_shell_execute"
},
"evidence": "sources [opencode_file_list] → sinks [opencode_shell_execute, opencode_project_init, opencode_tui_execute_command]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"opencode_file_list"
],
"sinks": [
"opencode_shell_execute",
"opencode_project_init",
"opencode_tui_execute_command"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"opencode_shell_execute\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"opencode_shell_execute\" appears to run shell commands or evaluate code (keyword \"shell\" 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": "opencode_shell_execute"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"opencode_tui_execute_command\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"opencode_tui_execute_command\" appears to run shell commands or evaluate code (keyword \"execute command\" 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": "opencode_tui_execute_command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"opencode_shell_execute\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"opencode_shell_execute\" 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": "opencode_shell_execute"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"opencode_tui_execute_command\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"opencode_tui_execute_command\" 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": "opencode_tui_execute_command"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"opencode_file_list"
],
"externalSink": [
"opencode_shell_execute",
"opencode_project_init",
"opencode_tui_execute_command"
],
"selfContained": false,
"path": [
"opencode_file_list",
"opencode_project_init"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: opencode_file_list → opencode_project_init."
}
],
"capabilities": [
{
"tool": "opencode_config_get",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_config_update",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_config_providers",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_events_poll",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_find_text",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_find_file",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_find_symbol",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_file_list",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "opencode_file_read",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_file_status",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_health",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_message_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_message_get",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_message_send",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_message_send_async",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_command_execute",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_shell_execute",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\" in tool name"
]
}
},
{
"tool": "opencode_path_get",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_vcs_info",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_instance_dispose",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_agent_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_command_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_lsp_status",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_formatter_status",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_mcp_status",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_mcp_add",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tool_ids",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tool_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_log",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_project_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_project_init",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"open_pr\""
]
}
},
{
"tool": "opencode_project_current",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_provider_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_provider_models",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_provider_auth_methods",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_provider_oauth_authorize",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_provider_oauth_callback",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_auth_set",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_create",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_get",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_delete",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_update",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_children",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_status",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_todo",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_init",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_abort",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_fork",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_share",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_unshare",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_diff",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_summarize",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_revert",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_unrevert",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_permission_list",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_permission",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_session_search",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_append_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_submit_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_clear_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_execute_command",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"execute command\" in tool name"
]
}
},
{
"tool": "opencode_tui_show_toast",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_open_help",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_open_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_open_models",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_tui_open_themes",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_setup",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_ask",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_reply",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_conversation",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_sessions_overview",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_context",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_wait",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_review_changes",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_provider_test",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_run",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_fire",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_check",
"tags": [],
"reasons": {}
},
{
"tool": "opencode_status",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "96c029c837c526a539010263be9d86eb8d3c4bc690b4e9e6ef95d5da78cc4f1b",
"stats": {
"tools": 80,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 0,
"low": 2,
"info": 0
}
}
}