Raw scan report

Session Mgmt — 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": "session-mgmt-mcp",
    "source": {
      "kind": "package",
      "origin": "session-mgmt-mcp"
    },
    "server": {
      "name": "session-mgmt-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-1.9"
  },
  "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 (21 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 (session_mgmt_mcp/cli.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/cli.py:167`): 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": "session_mgmt_mcp/cli.py"
      },
      "evidence": "] process = subprocess.Popen( cmd, stdout=subprocess.DEVNULL if not verbose else Non",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/cli.py",
        "line": 167,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/crackerjack_integration.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/crackerjack_integration.py:177`): 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": "session_mgmt_mcp/crackerjack_integration.py"
      },
      "evidence": "ss result = subprocess.run( cmd, check=False, capture_output",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/crackerjack_integration.py",
        "line": 177,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/server_core.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/server_core.py:63`): 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": "session_mgmt_mcp/server_core.py"
      },
      "evidence": "ilable result = subprocess.run( [\"crackerjack\", \"--version\"], check=False, c",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/server_core.py",
        "line": 63,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/server_optimized.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/server_optimized.py:371`): 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": "session_mgmt_mcp/server_optimized.py"
      },
      "evidence": "icator result = subprocess.run( [\"git\", \"log\", \"--oneline\", \"-20\", \"--since='24 hours ago'\"],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/server_optimized.py",
        "line": 371,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/tools/agent_analyzer.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/tools/agent_analyzer.py:63`): 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": "session_mgmt_mcp/tools/agent_analyzer.py"
      },
      "evidence": "ern\": r\"hardcoded.*path|shell=True|unsafe\", \"agent\": AgentType.SECURITY, \"confidence\": 0.85,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/tools/agent_analyzer.py",
        "line": 63,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/tools/crackerjack_tools.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/tools/crackerjack_tools.py:1330`): 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": "session_mgmt_mcp/tools/crackerjack_tools.py"
      },
      "evidence": "true\" result = subprocess.run( [\"python\", \"-m\", \"crackerjack\", \"--version\"], check=Fals",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/tools/crackerjack_tools.py",
        "line": 1330,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/tools/session_tools.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/tools/session_tools.py:363`): 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": "session_mgmt_mcp/tools/session_tools.py"
      },
      "evidence": "sync_result = subprocess.run( [\"uv\", \"sync\"], check=False, cwd",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/tools/session_tools.py",
        "line": 363,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/utils/file_utils.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/utils/file_utils.py:159`): 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": "session_mgmt_mcp/utils/file_utils.py"
      },
      "evidence": "ommand result = subprocess.run( [\"uv\", \"cache\", \"clean\"], capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/utils/file_utils.py",
        "line": 159,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/utils/git_operations.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/utils/git_operations.py:50`): 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": "session_mgmt_mcp/utils/git_operations.py"
      },
      "evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--show-toplevel\"], capture_output=",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/utils/git_operations.py",
        "line": 50,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (session_mgmt_mcp/utils/git_utils.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`session_mgmt_mcp/utils/git_utils.py:106`): 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": "session_mgmt_mcp/utils/git_utils.py"
      },
      "evidence": "fails.\"\"\" result = subprocess.run( command, cwd=current_dir, capture_output=True, t",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "session_mgmt_mcp/utils/git_utils.py",
        "line": 106,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (session_mgmt_mcp/health_checks.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`session_mgmt_mcp/health_checks.py:287`): 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": "session_mgmt_mcp/health_checks.py"
      },
      "evidence": "try: __import__(module_name) except ImportError: missing_imports.append(m",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "session_mgmt_mcp/health_checks.py",
        "line": 287,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (session_mgmt_mcp/llm_providers.py)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`session_mgmt_mcp/llm_providers.py:92`): 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": "session_mgmt_mcp/llm_providers.py"
      },
      "evidence": "\"anthropic\": __import__( \"session_mgmt_mcp.llm.providers.anthropic_provider\",",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "session_mgmt_mcp/llm_providers.py",
        "line": 92,
        "nonRuntime": false
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "search_reflections",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "session_welcome",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "permissions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "auto_compact",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "quality_monitor",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_llm_providers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "test_llm_providers",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_with_llm",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "chat_with_llm",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "configure_llm_provider",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "start",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "checkpoint",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "end",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "health_check",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "server_info",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "ping",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_team",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_team_knowledge",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_team_statistics",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "vote_on_reflection",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "608c58bb9bb151e6c333d731b38ef9979feff40a44df8997f4ba1a1fa806a73c",
  "stats": {
    "tools": 21,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 10,
      "medium": 2,
      "low": 0,
      "info": 0
    }
  }
}