Orygn Opa — 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": "@orygn/opa-mcp",
"source": {
"kind": "package",
"origin": "@orygn/opa-mcp"
},
"server": {
"name": "@orygn/opa-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 send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"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 (52 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-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/lib/opa-cli.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/lib/opa-cli.js:196`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. 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/lib/opa-cli.js"
},
"evidence": "ons). */ async eval(input, signal) { // Inline source becomes a temp file added to --data. if (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/lib/opa-cli.js",
"line": 196,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"rego_eval\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"rego_eval\" appears to run shell commands or evaluate code (keyword \"eval\" 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": "rego_eval"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"rego_eval_with_explain\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"rego_eval_with_explain\" appears to run shell commands or evaluate code (keyword \"eval\" 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": "rego_eval_with_explain"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"rego_eval_with_profile\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"rego_eval_with_profile\" appears to run shell commands or evaluate code (keyword \"eval\" 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": "rego_eval_with_profile"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"rego_eval_with_coverage\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"rego_eval_with_coverage\" appears to run shell commands or evaluate code (keyword \"eval\" 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": "rego_eval_with_coverage"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"opa_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"opa_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": "opa_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/lib/opa-cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/lib/opa-cli.js:196`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/lib/opa-cli.js"
},
"evidence": "ons). */ async eval(input, signal) { // Inline source becomes a temp file added to --data. if (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/lib/opa-cli.js",
"line": 196,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/lib/opa-cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/lib/opa-cli.js:390`): 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/lib/opa-cli.js"
},
"evidence": "file. */ async exec(input, signal) { if (input.inputPaths.length === 0) { throw new Error('",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/lib/opa-cli.js",
"line": 390,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/lib/subprocess.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/lib/subprocess.js:10`): 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/lib/subprocess.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { buildChildEnv } from './child-env.js'; /** * Per-stream capture ceilin",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/lib/subprocess.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([conftest_pull, opa_get_policy]) co-exist with external-action tools ([rego_eval, rego_eval_with_explain, rego_eval_with_profile, rego_eval_with_coverage, opa_exec]). 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": "conftest_pull → rego_eval"
},
"evidence": "untrusted [conftest_pull, opa_get_policy] → sinks [rego_eval, rego_eval_with_explain, rego_eval_with_profile, rego_eval_with_coverage, opa_exec]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"conftest_pull",
"opa_get_policy"
],
"sinks": [
"rego_eval",
"rego_eval_with_explain",
"rego_eval_with_profile",
"rego_eval_with_coverage",
"opa_exec"
]
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/server.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/server.js:41`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/server.js"
},
"evidence": "'u', id); await fetch(`https://opa-mcp-telemetry.gibbidaniel.workers.dev/ping?${params.toString()}`, {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/server.js",
"line": 41,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/helpers/playground-share.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/helpers/playground-share.js:89`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/helpers/playground-share.js"
},
"evidence": "response = await fetch('https://api.github.com/gists', { method: 'POST',",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/helpers/playground-share.js",
"line": 89,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"rego_eval\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"rego_eval\" 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": "rego_eval"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"rego_eval_with_explain\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"rego_eval_with_explain\" 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": "rego_eval_with_explain"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"rego_eval_with_profile\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"rego_eval_with_profile\" 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": "rego_eval_with_profile"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"rego_eval_with_coverage\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"rego_eval_with_coverage\" 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": "rego_eval_with_coverage"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"opa_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"opa_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": "opa_exec"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"conftest_pull",
"opa_get_policy"
],
"sensitiveSource": [],
"externalSink": [
"rego_eval",
"rego_eval_with_explain",
"rego_eval_with_profile",
"rego_eval_with_coverage",
"opa_exec"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "rego_capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "rego_check_schema",
"tags": [],
"reasons": {}
},
{
"tool": "rego_check",
"tags": [],
"reasons": {}
},
{
"tool": "rego_deps",
"tags": [],
"reasons": {}
},
{
"tool": "rego_format",
"tags": [],
"reasons": {}
},
{
"tool": "rego_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "rego_lint",
"tags": [],
"reasons": {}
},
{
"tool": "rego_migrate_v1",
"tags": [],
"reasons": {}
},
{
"tool": "rego_parse_ast",
"tags": [],
"reasons": {}
},
{
"tool": "opa_bundle_build",
"tags": [],
"reasons": {}
},
{
"tool": "opa_bundle_sign",
"tags": [],
"reasons": {}
},
{
"tool": "opa_bundle_verify",
"tags": [],
"reasons": {}
},
{
"tool": "conftest_pull",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "conftest_push",
"tags": [],
"reasons": {}
},
{
"tool": "conftest_test",
"tags": [],
"reasons": {}
},
{
"tool": "conftest_verify",
"tags": [],
"reasons": {}
},
{
"tool": "rego_bench",
"tags": [],
"reasons": {}
},
{
"tool": "rego_compile_query",
"tags": [],
"reasons": {}
},
{
"tool": "rego_eval",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "rego_eval_with_explain",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "rego_eval_with_profile",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "rego_eval_with_coverage",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "opa_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "rego_test_multiroot",
"tags": [],
"reasons": {}
},
{
"tool": "rego_test",
"tags": [],
"reasons": {}
},
{
"tool": "rego_coverage_gaps",
"tags": [],
"reasons": {}
},
{
"tool": "rego_describe_policy",
"tags": [],
"reasons": {}
},
{
"tool": "rego_explain_decision",
"tags": [],
"reasons": {}
},
{
"tool": "rego_explain_undefined",
"tags": [],
"reasons": {}
},
{
"tool": "rego_fix",
"tags": [],
"reasons": {}
},
{
"tool": "rego_format_write",
"tags": [],
"reasons": {}
},
{
"tool": "rego_generate_test_skeleton",
"tags": [],
"reasons": {}
},
{
"tool": "rego_infer_input_schema",
"tags": [],
"reasons": {}
},
{
"tool": "rego_playground_share",
"tags": [],
"reasons": {}
},
{
"tool": "rego_policy_diff",
"tags": [],
"reasons": {}
},
{
"tool": "rego_security_audit",
"tags": [],
"reasons": {}
},
{
"tool": "rego_suggest_fix",
"tags": [],
"reasons": {}
},
{
"tool": "rego_verify",
"tags": [],
"reasons": {}
},
{
"tool": "mcp_server_info",
"tags": [],
"reasons": {}
},
{
"tool": "opa_get_data",
"tags": [],
"reasons": {}
},
{
"tool": "opa_put_data",
"tags": [],
"reasons": {}
},
{
"tool": "opa_patch_data",
"tags": [],
"reasons": {}
},
{
"tool": "opa_delete_data",
"tags": [],
"reasons": {}
},
{
"tool": "opa_query_decision",
"tags": [],
"reasons": {}
},
{
"tool": "opa_compile_query",
"tags": [],
"reasons": {}
},
{
"tool": "opa_list_policies",
"tags": [],
"reasons": {}
},
{
"tool": "opa_get_policy",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "opa_put_policy",
"tags": [],
"reasons": {}
},
{
"tool": "opa_delete_policy",
"tags": [],
"reasons": {}
},
{
"tool": "opa_health",
"tags": [],
"reasons": {}
},
{
"tool": "opa_status",
"tags": [],
"reasons": {}
},
{
"tool": "opa_config",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e00891f3fa6ab4560568516d046e76772fc4e9b8e1611ec4b937993365b49a16",
"stats": {
"tools": 52,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 3,
"low": 5,
"info": 0
}
}
}