clawdefender

· v1.0.1

High Risk

Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards, or API responses, (3) validating URLs before fetching, (4) running security audits on your workspace. Protects agents from malicious content in untrusted data sources.

H:4 D:4 A:2 C:1

⚠️ Hazard Flags

EXEC FS_READ_USER FS_DELETE NET_EGRESS_ANY CREDS_FILES PI_WEB PI_DOCUMENTS

📋 Capabilities

Execution

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

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:

SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Base64 decode + execute pattern in: scripts/clawdefender.sh critical

Mitigation: Decode and review obfuscated content before use.

SSH key access patterns in: scripts/clawdefender.sh high

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

Cloud credential access patterns in: scripts/clawdefender.sh high

Mitigation: Verify legitimate need for cloud credential access.

Prompt injection patterns detected in: scripts/clawdefender.sh, SKILL.md 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 critical

Mitigation: Remove system modification commands

Command injection risk: COMMAND_INJECTION_USER_INPUT, MCP_CMD_REVERSE_SHELL, MCP_CMD_NETWORK_TOOLS 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

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:clawdefender:1.0.1",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T01:44:07.913Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "clawdefender",
    "version": "1.0.1",
    "format": "agent_skill",
    "description": "Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards, or API responses, (3) validating URLs before fetching, (4) running security audits on your workspace. Protects agents from malicious content in untrusted data sources.",
    "publisher": "ClawHub",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "6050cd0f99d72c7a1580882bd8d2b88f574c08af32160db4c298f2c16e327033",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": false,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": false,
      "writes_user_home": false,
      "writes_system": false,
      "can_delete": true
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": false,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [
      {
        "service": "code_hosting",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "actions": {
      "can_send_messages": false,
      "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": 2,
      "C": 1
    },
    "flags": [
      "EXEC",
      "FS_READ_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_FILES",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "BASE64_EXEC",
        "name": "Base64 Execute",
        "description": "Decodes and executes obfuscated code in: scripts/clawdefender.sh"
      },
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: scripts/clawdefender.sh"
      },
      {
        "code": "CRED_CLOUD",
        "name": "Cloud Credential Access",
        "description": "Accesses cloud credentials (AWS/GCP/Azure) in: scripts/clawdefender.sh"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: scripts/clawdefender.sh, SKILL.md"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/clawdefender.sh, SKILL.md"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS: 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, MCP_CMD_REVERSE_SHELL, MCP_CMD_NETWORK_TOOLS: User input used in command substitution - potential injection risk"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 8 security patterns (18 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A2: Service integrations detected",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "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": "Base64 decode + execute pattern in: scripts/clawdefender.sh",
        "severity": "critical",
        "mitigation": "Decode and review obfuscated content before use."
      },
      {
        "risk": "SSH key access patterns in: scripts/clawdefender.sh",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Cloud credential access patterns in: scripts/clawdefender.sh",
        "severity": "high",
        "mitigation": "Verify legitimate need for cloud credential access."
      },
      {
        "risk": "Prompt injection patterns detected in: scripts/clawdefender.sh, SKILL.md",
        "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",
        "severity": "critical",
        "mitigation": "Remove system modification commands"
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_USER_INPUT, MCP_CMD_REVERSE_SHELL, MCP_CMD_NETWORK_TOOLS",
        "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"
      }
    ],
    "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": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "scripts/clawdefender.sh",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/sanitize.sh",
      "file_path": "scripts/sanitize.sh"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/clawdefender.sh:655: findings=$(validate_url \"$2\")",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] scripts/clawdefender.sh:147: 'chmod 777'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_CMD_REVERSE_SHELL [CRITICAL] scripts/clawdefender.sh:151: 'nc -e'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_CMD_NETWORK_TOOLS [HIGH] scripts/clawdefender.sh:151: 'nc -e'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] scripts/clawdefender.sh:145: 'rm -rf /'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_PERMISSION_MANIPULATION [CRITICAL] scripts/clawdefender.sh:147: 'chmod 777'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/clawdefender.sh:1: #!/bin/bash",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] scripts/clawdefender.sh:23: RED='\\033[0;31m'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] scripts/clawdefender.sh:23: RED='\\033[0;31m'",
      "file_path": "scripts/clawdefender.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/sanitize.sh:1: #!/bin/bash",
      "file_path": "scripts/sanitize.sh"
    }
  ]
}