Cool Workflow — 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": "cool-workflow",
"source": {
"kind": "package",
"origin": "cool-workflow"
},
"server": {
"name": "cool-workflow"
}
},
"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": [
"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 (44 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-002",
"title": "Shell/command execution in server code (dist/mcp/tool-process.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/mcp/tool-process.js:42`): 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/mcp/tool-process.js"
},
"evidence": "or = void 0; const node_child_process_1 = require(\"node:child_process\"); const path = __importStar(require(\"node:path\"))",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/mcp/tool-process.js",
"line": 42,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/commit.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/commit.js:48`): 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/shell/commit.js"
},
"evidence": "ode:path\")); const node_child_process_1 = require(\"node:child_process\"); const fs_atomic_1 = require(\"./fs-atomic\"); con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/commit.js",
"line": 48,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/doctor.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/doctor.js:64`): 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/shell/doctor.js"
},
"evidence": "ode:path\")); const node_child_process_1 = require(\"node:child_process\"); const agent_config_1 = require(\"./agent-config\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/doctor.js",
"line": 64,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/execution-backend/agent.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/execution-backend/agent.js:75`): 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/shell/execution-backend/agent.js"
},
"evidence": "\"node:os\")); const node_child_process_1 = require(\"node:child_process\"); const local_1 = require(\"./local\"); const envel",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/execution-backend/agent.js",
"line": 75,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/execution-backend/container.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/execution-backend/container.js:13`): 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/shell/execution-backend/container.js"
},
"evidence": "unContainer; const node_child_process_1 = require(\"node:child_process\"); const probes_1 = require(\"./probes\"); const loc",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/execution-backend/container.js",
"line": 13,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/execution-backend/local.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/execution-backend/local.js: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": "dist/shell/execution-backend/local.js"
},
"evidence": "xecuteLocal; const node_child_process_1 = require(\"node:child_process\"); const hash_1 = require(\"../../core/hash\"); cons",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/execution-backend/local.js",
"line": 16,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/execution-backend/remote.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/execution-backend/remote.js:51`): 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/shell/execution-backend/remote.js"
},
"evidence": "ode:path\")); const node_child_process_1 = require(\"node:child_process\"); const envelopes_1 = require(\"./envelopes\"); con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/execution-backend/remote.js",
"line": 51,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/onramp.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/onramp.js:36`): 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/shell/onramp.js"
},
"evidence": "ode:path\")); const node_child_process_1 = require(\"node:child_process\"); exports.CURATED_SMOKE_MAP = [ { pat",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/onramp.js",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/shell/remote-source.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/shell/remote-source.js:25`): 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/shell/remote-source.js"
},
"evidence": "alizeRemote; const node_child_process_1 = require(\"node:child_process\"); const node_crypto_1 = require(\"node:crypto\"); c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/shell/remote-source.js",
"line": 25,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/shell/workflow-app-loader.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/shell/workflow-app-loader.js:232`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/shell/workflow-app-loader.js"
},
"evidence": "s const rawExport = require(entrypointPath); const selected = manifest.workflow.exportName && rawExport && typeo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/shell/workflow-app-loader.js",
"line": 232,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment in packaging/dev tooling (scripts/lang-policy-check.js)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/lang-policy-check.js:40`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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/lang-policy-check.js"
},
"evidence": "fig\", \".windsurfrules\", \".npmrc\", \".nvmrc\" ]); // `EXCEPT_PATHS` are written repo-root-relative, so tracked files must",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "scripts/lang-policy-check.js",
"line": 40,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/agents/claude-p-agent.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/agents/claude-p-agent.js: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": "scripts/agents/claude-p-agent.js"
},
"evidence": "nSync } = require(\"node:child_process\"); // Share the ONE canonical result contract with the codex/gemini/opencode // wr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/agents/claude-p-agent.js",
"line": 32,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal in packaging/dev tooling (scripts/validate-run-state-schema.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/validate-run-state-schema.js:39`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/validate-run-state-schema.js"
},
"evidence": "a; try { schema = require(SCHEMA_MODULE); } catch (e) { console.error(`validate-run-state-schema: FATAL — ca",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "scripts/validate-run-state-schema.js",
"line": 39,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "cw_dispatch",
"tags": [],
"reasons": {}
},
{
"tool": "cw_worker_output",
"tags": [],
"reasons": {}
},
{
"tool": "cw_node_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "cw_node_replay",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_register",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_score",
"tags": [],
"reasons": {}
},
{
"tool": "cw_worker_fail",
"tags": [],
"reasons": {}
},
{
"tool": "cw_topology_apply",
"tags": [],
"reasons": {}
},
{
"tool": "cw_summary_refresh",
"tags": [],
"reasons": {}
},
{
"tool": "cw_plan",
"tags": [],
"reasons": {}
},
{
"tool": "cw_app_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_app_validate",
"tags": [],
"reasons": {}
},
{
"tool": "cw_app_package",
"tags": [],
"reasons": {}
},
{
"tool": "cw_topology_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_topology_validate",
"tags": [],
"reasons": {}
},
{
"tool": "cw_topology_summary",
"tags": [],
"reasons": {}
},
{
"tool": "cw_topology_graph",
"tags": [],
"reasons": {}
},
{
"tool": "cw_summary_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_sandbox_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_sandbox_validate",
"tags": [],
"reasons": {}
},
{
"tool": "cw_sandbox_choose",
"tags": [],
"reasons": {}
},
{
"tool": "cw_sandbox_resolve",
"tags": [],
"reasons": {}
},
{
"tool": "cw_approve",
"tags": [],
"reasons": {}
},
{
"tool": "cw_reject",
"tags": [],
"reasons": {}
},
{
"tool": "cw_comment_add",
"tags": [],
"reasons": {}
},
{
"tool": "cw_handoff",
"tags": [],
"reasons": {}
},
{
"tool": "cw_review_policy",
"tags": [],
"reasons": {}
},
{
"tool": "cw_node_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_node_diff",
"tags": [],
"reasons": {}
},
{
"tool": "cw_node_replay_verify",
"tags": [],
"reasons": {}
},
{
"tool": "cw_worker_list",
"tags": [],
"reasons": {}
},
{
"tool": "cw_worker_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_worker_manifest",
"tags": [],
"reasons": {}
},
{
"tool": "cw_worker_validate",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_list",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_rank",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_select",
"tags": [],
"reasons": {}
},
{
"tool": "cw_candidate_reject",
"tags": [],
"reasons": {}
},
{
"tool": "cw_feedback_list",
"tags": [],
"reasons": {}
},
{
"tool": "cw_feedback_show",
"tags": [],
"reasons": {}
},
{
"tool": "cw_feedback_collect",
"tags": [],
"reasons": {}
},
{
"tool": "cw_feedback_task",
"tags": [],
"reasons": {}
},
{
"tool": "cw_feedback_resolve",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "91bfe99f66391bec424fc6c81a44009488deb09a90f50e3596a61ca7d57c689a",
"stats": {
"tools": 44,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 1,
"low": 3,
"info": 0
}
}
}