Everclaw — Inference You Own

{
  "meta": {
    "document_id": "ssds:auto:prompt-guard:0.10.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-06T14:14:58.514Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Everclaw — Inference You Own",
    "version": "0.10.0",
    "format": "agent_skill",
    "description": "Advanced prompt injection defense system for Clawdbot with HiveFence network integration. Protects against direct/indirect injection attacks in group chats with multi-language detection (EN/KO/JA/ZH), severity scoring, automatic logging, and configurable security policies. Connects to the distributed HiveFence threat intelligence network for collective defense.",
    "publisher": "ClawHub",
    "source": {
      "channel": "clawhub",
      "slug": "everclaw-inference",
      "owner": "DavidAJohnston",
      "downloads": 675,
      "stars": 0
    },
    "artifact": {
      "sha256": "f514860851c69ab079e75bd896f8e372df57c3fb780afa160975899e2f85cc11",
      "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": true,
      "reads_keychain": true
    },
    "services": [
      {
        "service": "code_hosting",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "actions": {
      "can_send_messages": false,
      "can_post_public": true,
      "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",
      "CREDS_BROWSER",
      "CREDS_KEYCHAIN",
      "ACT_POST_PUBLIC",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PIPE_TO_SHELL",
        "name": "Pipe to Shell",
        "description": "Downloads and executes remote code (curl|bash pattern) in: SKILL.md, scripts/swap.sh, scripts/install-with-deps.sh, scripts/install-everclaw.sh, scripts/gateway-guardian.sh, README.md"
      },
      {
        "code": "SECURITY_BYPASS",
        "name": "Security Bypass",
        "description": "Attempts to disable security features in: prompt-guard/scripts/detect.py"
      },
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: prompt-guard/SKILL.md, prompt-guard/scripts/detect.py"
      },
      {
        "code": "CRED_BROWSER",
        "name": "Browser Profile Access",
        "description": "Accesses browser cookies/profiles in: prompt-guard/SKILL.md"
      },
      {
        "code": "CRED_KEYCHAIN",
        "name": "Keychain Access",
        "description": "Accesses system keychain in: SKILL.md, scripts/x402-client.mjs, scripts/swap.sh, scripts/start.sh, scripts/mor-launch-headless.sh, scripts/install-proxy.sh, scripts/everclaw-wallet.mjs, scripts/coingecko-x402.mjs, README.md"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: SKILL.md, scripts/router.mjs, scripts/install-proxy.sh, prompt-guard/SKILL.md, prompt-guard/scripts/detect.py, prompt-guard/README.md"
      },
      {
        "code": "HIDDEN_INSTRUCTIONS",
        "name": "Hidden Instructions",
        "description": "Contains hidden instructions in comments/invisible chars in: SKILL.md"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: SKILL.md, scripts/install-proxy.sh, scripts/gateway-guardian.sh, scripts/diagnose.sh, scripts/always-on.sh"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: SKILL.md, scripts/install-with-deps.sh, scripts/always-on.sh, README.md, prompt-guard/scripts/detect.py, prompt-guard/scripts/audit.py"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/install.sh, scripts/install-everclaw.sh, scripts/fix-pii-all-repos.sh, scripts/filter-repo-pii.sh, scripts/everclaw-deps.mjs, scripts/bootstrap-gateway.mjs, scripts/bootstrap-everclaw.mjs"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: scripts/morpheus-proxy.mjs"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PROCESS_MANIPULATION, MCP_SYS_FILE_DESTRUCTION, TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL, TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_PRIVILEGE_ESCALATION: Instructs agent to install external binary or package"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "MCP_SQL_BLIND, COMMAND_INJECTION_USER_INPUT, TIRITH_DOTFILE_OVERWRITE, MCP_CMD_DANGEROUS_SYSTEM, MCP_SCRIPT_TAGS: Blind SQL injection, system table access, or stored procedure abuse"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "MCP_EXFIL_CONVERSATION, DATA_EXFIL_NETWORK_REQUESTS: Conversation, clipboard, or keystroke exfiltration patterns"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 15 security patterns (72 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_POST",
        "reason": "Can post publicly"
      },
      {
        "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: SKILL.md, scripts/swap.sh, scripts/install-with-deps.sh, scripts/install-everclaw.sh, scripts/gateway-guardian.sh, README.md",
        "severity": "critical",
        "mitigation": "Do not execute. Review source for malicious intent."
      },
      {
        "risk": "Security bypass pattern detected in: prompt-guard/scripts/detect.py",
        "severity": "critical",
        "mitigation": "This skill attempts to disable security features. Do not use."
      },
      {
        "risk": "SSH key access patterns in: prompt-guard/SKILL.md, prompt-guard/scripts/detect.py",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Keychain/credential store access in: SKILL.md, scripts/x402-client.mjs, scripts/swap.sh, scripts/start.sh, scripts/mor-launch-headless.sh, scripts/install-proxy.sh, scripts/everclaw-wallet.mjs, scripts/coingecko-x402.mjs, README.md",
        "severity": "high",
        "mitigation": "Block keychain access or use isolated environment."
      },
      {
        "risk": "Prompt injection patterns detected in: SKILL.md, scripts/router.mjs, scripts/install-proxy.sh, prompt-guard/SKILL.md, prompt-guard/scripts/detect.py, prompt-guard/README.md",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD, MCP_SYS_CRITICAL_ACCESS, MCP_SYS_PROCESS_MANIPULATION, MCP_SYS_FILE_DESTRUCTION, TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL, TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_PRIVILEGE_ESCALATION",
        "severity": "critical",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: MCP_SQL_BLIND, COMMAND_INJECTION_USER_INPUT, TIRITH_DOTFILE_OVERWRITE, MCP_CMD_DANGEROUS_SYSTEM, MCP_SCRIPT_TAGS",
        "severity": "critical",
        "mitigation": "Remove SQL exploitation patterns."
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: MCP_EXFIL_CONVERSATION, DATA_EXFIL_NETWORK_REQUESTS",
        "severity": "high",
        "mitigation": "Remove references to exfiltrating conversation data or monitoring input."
      }
    ],
    "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": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/x402-client.mjs",
      "file_path": "scripts/x402-client.mjs"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/venice-key-monitor.sh",
      "file_path": "scripts/venice-key-monitor.sh"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/venice-402-watchdog.sh",
      "file_path": "scripts/venice-402-watchdog.sh"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "scripts/swap.sh",
      "file_path": "scripts/swap.sh"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "scripts/stop.sh",
      "file_path": "scripts/stop.sh"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "scripts/start.sh",
      "file_path": "scripts/start.sh"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "scripts/setup.mjs",
      "file_path": "scripts/setup.mjs"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "scripts/session.sh",
      "file_path": "scripts/session.sh"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:63: note: \"curl | bash installer available but users should review scripts before ex",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "INSTRUCTED_GIT_CLONE_AND_BUILD [MEDIUM] SKILL.md:276: git clone https://github.com/profbernardoj/everclaw.git ~/.openclaw/workspace/sk",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] SKILL.md:1975: # Configure macOS to never sleep (requires sudo)",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/venice-key-monitor.sh:1: #!/bin/bash",
      "file_path": "scripts/venice-key-monitor.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/venice-402-watchdog.sh:1: #!/bin/bash",
      "file_path": "scripts/venice-402-watchdog.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/swap.sh:138: TX_HASH=$(echo \"$RESULT\" | grep \"transactionHash\" | awk '{print $2}')",
      "file_path": "scripts/swap.sh"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/swap.sh:1: #!/bin/bash",
      "file_path": "scripts/swap.sh"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] scripts/swap.sh:87: # Check if cast (Foundry) is available",
      "file_path": "scripts/swap.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/stop.sh:1: #!/bin/bash",
      "file_path": "scripts/stop.sh"
    }
  ]
}