Cc Agent — 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": "@gonzih/cc-agent",
"source": {
"kind": "package",
"origin": "@gonzih/cc-agent"
},
"server": {
"name": "@gonzih/cc-agent"
}
},
"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-1.13"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"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",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"code-exec",
"external-sink",
"sensitive-source",
"untrusted-input"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (47 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-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: work_on_issue → get_logs ⇒ send_message. Untrusted input is ingested, private data is read, and it can be sent to an external sink — and at least one leg is a direct schema wire (⇒), where a producer's output drops straight into a free-text parameter of the next tool, so the chain needs little agent cooperation. Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "work_on_issue → get_logs → send_message"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"work_on_issue"
],
"sources": [
"get_logs"
],
"sinks": [
"spawn_agent",
"send_message",
"spawn_from_profile"
],
"path": [
"work_on_issue",
"get_logs",
"send_message"
],
"edges": [
{
"from": "work_on_issue",
"to": "get_logs",
"kind": "agent-mediated"
},
{
"from": "get_logs",
"to": "send_message",
"kind": "schema-wired"
}
],
"wired": true
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (dist/docker.js)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/docker.js:71`): 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": "dist/docker.js"
},
"evidence": "nst npmrcPath = `${home}/.npmrc`; if (existsSync(npmrcPath)) { args.push(\"-v\", `${npmrcPath}:/root/.npmrc:ro",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "dist/docker.js",
"line": 71,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"spawn_agent\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_agent\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "spawn_agent"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"spawn_from_profile\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"spawn_from_profile\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "spawn_from_profile"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/agent.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/agent.js:1`): 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/agent.js"
},
"evidence": "port { execFile } from \"child_process\"; import { existsSync } from \"fs\"; import { mkdtemp, rm, appendFile, mkdir, readFi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/agent.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/claude.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/claude.js:2`): 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/claude.js"
},
"evidence": "import { spawn } from \"child_process\"; import { EventEmitter } from \"events\"; import { join } from \"path\"; import { tmp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/claude.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/docker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/docker.js:1`): 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/docker.js"
},
"evidence": "execFile, spawn } from \"child_process\"; import { EventEmitter } from \"events\"; import { existsSync, readFileSync } from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/docker.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/drivers/aider.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/drivers/aider.js:3`): 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/drivers/aider.js"
},
"evidence": "import { spawn } from \"child_process\"; import { getPricing } from \"./pricing.js\"; import { BaseAgentProcess } from \"./t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/drivers/aider.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/drivers/amp.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/drivers/amp.js:2`): 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/drivers/amp.js"
},
"evidence": "import { spawn } from \"child_process\"; import { getPricing } from \"./pricing.js\"; import { BaseAgentProcess } from \"./t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/drivers/amp.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/drivers/claude-code.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/drivers/claude-code.js:37`): 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/drivers/claude-code.js"
},
"evidence": "return false; } spawn(options) { // Extract ollama config encoded in env by agent.ts const ollam",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/drivers/claude-code.js",
"line": 37,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/drivers/codex.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/drivers/codex.js:2`): 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/drivers/codex.js"
},
"evidence": "import { spawn } from \"child_process\"; import { getPricing } from \"./pricing.js\"; import { BaseAgentProcess } from \"./t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/drivers/codex.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/drivers/gemini.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/drivers/gemini.js:2`): 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/drivers/gemini.js"
},
"evidence": "import { spawn } from \"child_process\"; import { getPricing } from \"./pricing.js\"; import { BaseAgentProcess } from \"./t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/drivers/gemini.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/drivers/openai-compatible.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/drivers/openai-compatible.js:17`): 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/drivers/openai-compatible.js"
},
"evidence": "port { execFile } from \"child_process\"; import { promisify } from \"util\"; import { writeFile, readFile, readdir } from \"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/drivers/openai-compatible.js",
"line": 17,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:40`): 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/index.js"
},
"evidence": "port { execFile } from \"child_process\"; import { promisify } from \"util\"; import { existsSync, readFileSync } from \"fs\";",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 40,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_agent\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_agent\" 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": "spawn_agent"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"spawn_from_profile\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"spawn_from_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": "spawn_from_profile"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"work_on_issue"
],
"sensitiveSource": [
"get_logs"
],
"externalSink": [
"spawn_agent",
"send_message",
"spawn_from_profile"
],
"selfContained": false,
"path": [
"work_on_issue",
"get_logs",
"send_message"
],
"pathWired": true,
"description": "A cross-tool exfiltration chain exists: work_on_issue → get_logs ⇒ send_message."
}
],
"capabilities": [
{
"tool": "spawn_agent",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "get_job_status",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for_job",
"tags": [],
"reasons": {}
},
{
"tool": "get_job_output",
"tags": [],
"reasons": {}
},
{
"tool": "list_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_job",
"tags": [],
"reasons": {}
},
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "cost_summary",
"tags": [],
"reasons": {}
},
{
"tool": "get_version",
"tags": [],
"reasons": {}
},
{
"tool": "create_profile",
"tags": [],
"reasons": {}
},
{
"tool": "list_profiles",
"tags": [],
"reasons": {}
},
{
"tool": "delete_profile",
"tags": [],
"reasons": {}
},
{
"tool": "create_plan",
"tags": [],
"reasons": {}
},
{
"tool": "get_logs",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_logs\""
]
}
},
{
"tool": "wake_job",
"tags": [],
"reasons": {}
},
{
"tool": "list_model_ratings",
"tags": [],
"reasons": {}
},
{
"tool": "list_project_issues",
"tags": [],
"reasons": {}
},
{
"tool": "work_on_issue",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "comment_on_issue",
"tags": [],
"reasons": {}
},
{
"tool": "close_issue",
"tags": [],
"reasons": {}
},
{
"tool": "approve_job",
"tags": [],
"reasons": {}
},
{
"tool": "set_job_score",
"tags": [],
"reasons": {}
},
{
"tool": "get_learnings",
"tags": [],
"reasons": {}
},
{
"tool": "clear_learnings",
"tags": [],
"reasons": {}
},
{
"tool": "get_wiki",
"tags": [],
"reasons": {}
},
{
"tool": "get_wiki_page",
"tags": [],
"reasons": {}
},
{
"tool": "update_wiki_page",
"tags": [],
"reasons": {}
},
{
"tool": "delete_wiki_page",
"tags": [],
"reasons": {}
},
{
"tool": "list_wiki_pages",
"tags": [],
"reasons": {}
},
{
"tool": "docker_ps",
"tags": [],
"reasons": {}
},
{
"tool": "list_token_status",
"tags": [],
"reasons": {}
},
{
"tool": "spawn_from_profile",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "list_crons",
"tags": [],
"reasons": {}
},
{
"tool": "create_cron",
"tags": [],
"reasons": {}
},
{
"tool": "delete_cron",
"tags": [],
"reasons": {}
},
{
"tool": "update_cron",
"tags": [],
"reasons": {}
},
{
"tool": "list_notifications",
"tags": [],
"reasons": {}
},
{
"tool": "list_active_repos",
"tags": [],
"reasons": {}
},
{
"tool": "get_pubsub_status",
"tags": [],
"reasons": {}
},
{
"tool": "list_drivers",
"tags": [],
"reasons": {}
},
{
"tool": "export_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "get_cost_report",
"tags": [],
"reasons": {}
},
{
"tool": "search_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "swarm_task",
"tags": [],
"reasons": {}
},
{
"tool": "get_swarm_status",
"tags": [],
"reasons": {}
},
{
"tool": "generate_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "get_workflow_status",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "fdf426cf778e2b1c6ed68ab17eef39a1c3ea94c37eb6be44bd9775d7e091471e",
"stats": {
"tools": 47,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 13,
"medium": 0,
"low": 2,
"info": 0
}
}
}