Raw scan report

Sugarai — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.9.0",
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "target": {
    "id": "sugarai",
    "source": {
      "kind": "package",
      "origin": "sugarai"
    },
    "server": {
      "name": "sugarai"
    }
  },
  "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-1.9"
  },
  "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 (17 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 (sugar/agent/subagent_manager.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`sugar/agent/subagent_manager.py:120`): 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": "sugar/agent/subagent_manager.py"
      },
      "evidence": "n config async def spawn( self, task_id: str, prompt: str, task_context: Optional[s",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "sugar/agent/subagent_manager.py",
        "line": 120,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (sugar/discovery/github_watcher.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`sugar/discovery/github_watcher.py:97`): 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": "sugar/discovery/github_watcher.py"
      },
      "evidence": "le result = subprocess.run( [gh_command, \"--version\"], capture_output=True, text=True, timeo",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "sugar/discovery/github_watcher.py",
        "line": 97,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (sugar/executor/hooks.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`sugar/executor/hooks.py: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": "sugar/executor/hooks.py"
      },
      "evidence": "result = subprocess.run( cmd, shell=True, cwd",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "sugar/executor/hooks.py",
        "line": 64,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (sugar/integrations/github.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`sugar/integrations/github.py:169`): 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": "sugar/integrations/github.py"
      },
      "evidence": "d)}\") result = subprocess.run( cmd, capture_output=True, text=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "sugar/integrations/github.py",
        "line": 169,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (sugar/main.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`sugar/main.py:1446`): 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": "sugar/main.py"
      },
      "evidence": "process = subprocess.Popen(cmd, stdout=sys.stdout, stderr=sys.stderr) process.wait()",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "sugar/main.py",
        "line": 1446,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (sugar/mcp/server.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`sugar/mcp/server.py:320`): 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": "sugar/mcp/server.py"
      },
      "evidence": "y: result = subprocess.run( cmd, capture_output=True, text=T",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "sugar/mcp/server.py",
        "line": 320,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_goose_integration.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_goose_integration.py:62`): 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": "tests/test_goose_integration.py"
      },
      "evidence": "roject.\"\"\" result = subprocess.run( [sugar_cmd, \"init\"], cwd=temp_project_dir, capture_outpu",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_goose_integration.py",
        "line": 62,
        "nonRuntime": true
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "search_memory",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "store_learning",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_project_context",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "recall",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_recent_memories",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "analyze_issue",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_response",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_codebase",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_similar_issues",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "suggest_labels",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "validate_response",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sugar_add_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sugar_list_tasks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sugar_view_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sugar_update_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sugar_task_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sugar_remove_task",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "f85d122435cee24dcf55bd0504b501fb8e8c015a5a2ea7e1deeb545a7d285b13",
  "stats": {
    "tools": 17,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 6,
      "medium": 0,
      "low": 1,
      "info": 0
    }
  }
}