Cli Bridge — 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": "cli-bridge-mcp",
"source": {
"kind": "package",
"origin": "cli-bridge-mcp"
},
"server": {
"name": "cli-bridge-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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"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 (35 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-001",
"title": "Dynamic code execution in server code (src/cli_bridge/workflows.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/workflows.py:161`): 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": "src/cli_bridge/workflows.py"
},
"evidence": "s*\\(\"), \"high\", \"Use of eval()\", \"eval on untrusted input is arbitrary code execution; parse explicitly instead.\"),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/cli_bridge/workflows.py",
"line": 161,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/budget.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/budget.py:14`): 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": "src/cli_bridge/budget.py"
},
"evidence": "vailable never blocks a spawn (the gates fail open, not closed: a broken local sqlite must not take the council down). F",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/budget.py",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/buildloop.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/buildloop.py:197`): 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": "src/cli_bridge/buildloop.py"
},
"evidence": "zone_label} p = subprocess.run(list(dod_cmd), cwd=target_dir, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/buildloop.py",
"line": 197,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/lanes.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/lanes.py:548`): 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": "src/cli_bridge/lanes.py"
},
"evidence": "try: proc = subprocess.run([bin_name, \"models\"], capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/lanes.py",
"line": 548,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/reports.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/reports.py:213`): 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": "src/cli_bridge/reports.py"
},
"evidence": "LY_LIMIT is enforced at spawn (any lane). \" \"_CREDITS_PER_1K makes CLI_BRIDGE_DAILY_CREDIT_CAP enforcea",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/reports.py",
"line": 213,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/runner.py:114`): 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": "src/cli_bridge/runner.py"
},
"evidence": "if _IS_WINDOWS: subprocess.run([\"taskkill\", \"/F\", \"/T\", \"/PID\", str(pid)], capture_output",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/runner.py",
"line": 114,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/workflows.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/workflows.py:58`): 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": "src/cli_bridge/workflows.py"
},
"evidence": "try: proc = subprocess.run( [\"git\", \"-C\", cwd or \".\", \"diff\", base], capture_output=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/workflows.py",
"line": 58,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/cli_bridge/worktrees.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli_bridge/worktrees.py:41`): 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": "src/cli_bridge/worktrees.py"
},
"evidence": "]: try: p = subprocess.run([\"git\", *args], cwd=cwd, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli_bridge/worktrees.py",
"line": 41,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "ask_all",
"tags": [],
"reasons": {}
},
{
"tool": "ask_all_async",
"tags": [],
"reasons": {}
},
{
"tool": "job_status",
"tags": [],
"reasons": {}
},
{
"tool": "job_result",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "job_cancel",
"tags": [],
"reasons": {}
},
{
"tool": "jobs_list",
"tags": [],
"reasons": {}
},
{
"tool": "batch_run",
"tags": [],
"reasons": {}
},
{
"tool": "workflow",
"tags": [],
"reasons": {}
},
{
"tool": "conversations_list",
"tags": [],
"reasons": {}
},
{
"tool": "conversation_show",
"tags": [],
"reasons": {}
},
{
"tool": "list_models",
"tags": [],
"reasons": {}
},
{
"tool": "doctor",
"tags": [],
"reasons": {}
},
{
"tool": "setup",
"tags": [],
"reasons": {}
},
{
"tool": "usage_report",
"tags": [],
"reasons": {}
},
{
"tool": "usage_budget",
"tags": [],
"reasons": {}
},
{
"tool": "lane_stats",
"tags": [],
"reasons": {}
},
{
"tool": "reset_lane_state",
"tags": [],
"reasons": {}
},
{
"tool": "ask_cascade",
"tags": [],
"reasons": {}
},
{
"tool": "route_plan",
"tags": [],
"reasons": {}
},
{
"tool": "ask_best",
"tags": [],
"reasons": {}
},
{
"tool": "rate_lane",
"tags": [],
"reasons": {}
},
{
"tool": "set_lane_cost",
"tags": [],
"reasons": {}
},
{
"tool": "review_diff",
"tags": [],
"reasons": {}
},
{
"tool": "security_review",
"tags": [],
"reasons": {}
},
{
"tool": "ask_build",
"tags": [],
"reasons": {}
},
{
"tool": "ask_build_isolated",
"tags": [],
"reasons": {}
},
{
"tool": "job_tail",
"tags": [],
"reasons": {}
},
{
"tool": "build_steer",
"tags": [],
"reasons": {}
},
{
"tool": "debate",
"tags": [],
"reasons": {}
},
{
"tool": "consensus",
"tags": [],
"reasons": {}
},
{
"tool": "challenge",
"tags": [],
"reasons": {}
},
{
"tool": "premortem",
"tags": [],
"reasons": {}
},
{
"tool": "test_plan",
"tags": [],
"reasons": {}
},
{
"tool": "commit_msg",
"tags": [],
"reasons": {}
},
{
"tool": "pr_describe",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "78e15f9eabccbbfe8942d64da7e4e4a676d66f14751a7084e7044fd1749df75f",
"stats": {
"tools": 35,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 0,
"info": 0
}
}
}