LobsterGuard

· v6.1.0

High Risk

"Bilingual security auditor for OpenClaw. 68 checks across 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10 coverage, forensic detection, real-time threat interception, and guided hardening."

H:4 D:4 A:3 C:1

⚠️ Hazard Flags

EXEC PRIVILEGED PERSISTENCE FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_WRITE_SYSTEM FS_DELETE NET_EGRESS_ANY NET_INGRESS CREDS_ENV CREDS_FILES ACT_SEND_MESSAGE PI_WEB PI_DOCUMENTS

📋 Capabilities

Execution

✅ Shell execution
❌ Code execution
❌ Install dependencies
✅ Persistence
Privilege: admin

Filesystem

✅ Read workspace
✅ Write workspace
✅ Read home
✅ Write home
❌ Read system
✅ Delete

Network

Egress: any
✅ Ingress

Credentials

✅ Environment vars
✅ Credential files
❌ Browser data
❌ Keychain

Actions

✅ send messages❌ post public❌ purchase❌ transfer money❌ deploy❌ delete external

🔒 Containment

Level: maximum

Required:

APPROVE_SEND: Can send messages
SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Pipe-to-shell pattern detected (curl|bash) in: scripts/check.py critical

Mitigation: Do not execute. Review source for malicious intent.

SSH key access patterns in: extension/dist/watcher.js, scripts/check.py, scripts/skill_scanner.py high

Mitigation: Verify legitimate need for SSH access. Consider sandboxing.

Cloud credential access patterns in: scripts/skill_scanner.py high

Mitigation: Verify legitimate need for cloud credential access.

Prompt injection patterns detected in: scripts/check.py high

Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.

Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PRIVILEGE_ESCALATION, MCP_SYS_PROCESS_MANIPULATION, INSTRUCTED_GIT_CLONE_AND_BUILD, TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL critical

Mitigation: Remove system modification commands

Command injection risk: COMMAND_INJECTION_USER_INPUT, TIRITH_DOTFILE_OVERWRITE, MCP_SQL_BLIND, COMMAND_INJECTION_EVAL, COMMAND_INJECTION_OS_SYSTEM, COMMAND_INJECTION_SHELL_TRUE, MCP_CMD_DANGEROUS_SYSTEM critical

Mitigation: Validate and sanitize all user inputs before using in commands

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_SENSITIVE_FILES high

Mitigation: Ensure network access is necessary and documented

Want a deeper analysis?

This report was generated by static analysis. Get an LLM-powered deep review with behavioral reasoning and attack surface mapping.

🧠 Deep Analysis — $5.00

🚨 Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

📄 Raw SSDS JSON click to expand

{
  "meta": {
    "document_id": "ssds:auto:lobsterguard:6.1.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T15:36:16.946Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "LobsterGuard",
    "version": "6.1.0",
    "format": "agent_skill",
    "description": "\"Bilingual security auditor for OpenClaw. 68 checks across 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10 coverage, forensic detection, real-time threat interception, and guided hardening.\"",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "0134245c011033babb131b4fd4ccb745364e29c8e28f026921fca570a3298f72",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "admin",
      "can_install_deps": false,
      "can_persist": true
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": true,
      "writes_system": true,
      "can_delete": true
    },
    "network": {
      "egress": "any",
      "ingress": true
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [
      {
        "service": "messaging",
        "operations": [
          "read",
          "write"
        ]
      },
      {
        "service": "code_hosting",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "actions": {
      "can_send_messages": true,
      "can_post_public": false,
      "can_purchase": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": false
    },
    "prompt_injection_surfaces": [
      "web",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PRIVILEGED",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_WRITE_SYSTEM",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "NET_INGRESS",
      "CREDS_ENV",
      "CREDS_FILES",
      "ACT_SEND_MESSAGE",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PIPE_TO_SHELL",
        "name": "Pipe to Shell",
        "description": "Downloads and executes remote code (curl|bash pattern) in: scripts/check.py"
      },
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: extension/dist/watcher.js, scripts/check.py, scripts/skill_scanner.py"
      },
      {
        "code": "CRED_CLOUD",
        "name": "Cloud Credential Access",
        "description": "Accesses cloud credentials (AWS/GCP/Azure) in: scripts/skill_scanner.py"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: scripts/check.py"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: extension/dist/index.js, extension/dist/interceptor.js, extension/dist/watcher.js, install.sh, scripts/check.py, scripts/fix_engine.py, scripts/skill_scanner.py"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: extension/dist/interceptor.js, install.sh, README.md, scripts/check.py, scripts/fix_engine.py, scripts/skill_scanner.py, SKILL.md"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: install.sh, scripts/check.py, scripts/fix_engine.py, scripts/quarantine_watcher.py, scripts/skill_scanner.py"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: scripts/check.py"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PRIVILEGE_ESCALATION, MCP_SYS_PROCESS_MANIPULATION, INSTRUCTED_GIT_CLONE_AND_BUILD, TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL: Modifying system permissions or configuration"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "COMMAND_INJECTION_USER_INPUT, TIRITH_DOTFILE_OVERWRITE, MCP_SQL_BLIND, COMMAND_INJECTION_EVAL, COMMAND_INJECTION_OS_SYSTEM, COMMAND_INJECTION_SHELL_TRUE, MCP_CMD_DANGEROUS_SYSTEM: User input used in command substitution - potential injection risk"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_SENSITIVE_FILES: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 12 security patterns (36 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A3: External actions (deploy/message/post)",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "control": "APPROVE_SEND",
        "reason": "Can send messages"
      },
      {
        "control": "SANDBOX_CONTAINER",
        "reason": "Code execution capability"
      }
    ],
    "recommended": [
      {
        "control": "LOG_ACTIONS",
        "reason": "Audit trail for all actions"
      }
    ],
    "uncontained_risk": "Risk level depends on manual review of actual capabilities."
  },
  "risks": {
    "risks": [
      {
        "risk": "Pipe-to-shell pattern detected (curl|bash) in: scripts/check.py",
        "severity": "critical",
        "mitigation": "Do not execute. Review source for malicious intent."
      },
      {
        "risk": "SSH key access patterns in: extension/dist/watcher.js, scripts/check.py, scripts/skill_scanner.py",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Cloud credential access patterns in: scripts/skill_scanner.py",
        "severity": "high",
        "mitigation": "Verify legitimate need for cloud credential access."
      },
      {
        "risk": "Prompt injection patterns detected in: scripts/check.py",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PRIVILEGE_ESCALATION, MCP_SYS_PROCESS_MANIPULATION, INSTRUCTED_GIT_CLONE_AND_BUILD, TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL",
        "severity": "critical",
        "mitigation": "Remove system modification commands"
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_USER_INPUT, TIRITH_DOTFILE_OVERWRITE, MCP_SQL_BLIND, COMMAND_INJECTION_EVAL, COMMAND_INJECTION_OS_SYSTEM, COMMAND_INJECTION_SHELL_TRUE, MCP_CMD_DANGEROUS_SYSTEM",
        "severity": "critical",
        "mitigation": "Validate and sanitize all user inputs before using in commands"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_SENSITIVE_FILES",
        "severity": "high",
        "mitigation": "Ensure network access is necessary and documented"
      }
    ],
    "limitations": [
      "Static analysis only - runtime behavior not verified"
    ]
  },
  "incident_response": {
    "kill_switch": [
      "Stop the agent process"
    ],
    "containment": [
      "Review logs for unexpected actions"
    ],
    "recovery": [
      "Depends on skill capabilities"
    ]
  },
  "evidence": [
    {
      "evidence_id": "EV:file-1",
      "type": "file_excerpt",
      "title": "extension/dist/fix_tool.js",
      "file_path": "extension/dist/fix_tool.js"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "extension/dist/index.js",
      "file_path": "extension/dist/index.js"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "extension/dist/interceptor.js",
      "file_path": "extension/dist/interceptor.js"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "extension/dist/types.js",
      "file_path": "extension/dist/types.js"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "extension/dist/watcher.js",
      "file_path": "extension/dist/watcher.js"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "extension/package.json",
      "file_path": "extension/package.json"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "install.sh",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "scripts/autoscan.py",
      "file_path": "scripts/autoscan.py"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "scripts/check.py",
      "file_path": "scripts/check.py"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] extension/dist/interceptor.js:150: pattern: \"(echo|cat|sed).*(/etc/ssh/sshd_config|/etc/sudoers)\",",
      "file_path": "extension/dist/interceptor.js"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] extension/dist/watcher.js:68: path: \"/etc/sudoers\",",
      "file_path": "extension/dist/watcher.js"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] install.sh:75: OC_USER=\"$(ps aux | grep -i 'openclaw' | grep -v grep | head -1 | awk '{print $1",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] install.sh:70: chown -R \"$OC_USER:$OC_USER\" \"$CONFIG_DIR\"",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] install.sh:251: [ -d \"$SKILL_DIR\" ] && rm -rf \"$SKILL_DIR\" && log_ok \"Skill eliminado\"",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_PERMISSION_MANIPULATION [CRITICAL] install.sh:172: chown root:root \"$SKILL_DIR/scripts/check.py\" 2>/dev/null || true",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] install.sh:1: #!/usr/bin/env bash",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SYS_PRIVILEGE_ESCALATION [CRITICAL] install.sh:198: if su - \"$OC_USER\" -c \"crontab -l 2>/dev/null\" | grep -q \"cleanup.py\"; then",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SYS_PROCESS_MANIPULATION [HIGH] install.sh:138: echo \"$OC_USER ALL=(ALL) NOPASSWD: /bin/mount, /usr/bin/kill, /usr/bin/killall, ",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] install.sh:9: RED=\"\\033[0;31m\"",
      "file_path": "install.sh"
    }
  ]
}