πŸ›‘οΈ SafeAgentSkills

Openclaw Security Guard

Β· v1.0.0

High Risk

Security audit CLI + live dashboard for OpenClaw. Scans for secrets, config issues, prompt injections, vulnerable dependencies, and unverified MCP servers. Zero telemetry.

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

⚠️ Hazard Flags

EXEC CODE_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_FILES CREDS_BROWSER PI_WEB PI_DOCUMENTS

πŸ“‹ Capabilities

Execution

  • βœ… Shell execution
  • βœ… Code execution
  • βœ… Install dependencies
  • βœ… Persistence
  • Privilege: admin

Filesystem

  • βœ… Read workspace
  • βœ… Write workspace
  • βœ… Read home
  • βœ… Write home
  • ❌ Read system
  • βœ… Delete

Network

  • Egress: any
  • βœ… Ingress

Credentials

  • ❌ Environment vars
  • βœ… Credential files
  • βœ… Browser data
  • ❌ Keychain

Actions

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

πŸ”’ Containment

Level: maximum

Required:
  • SANDBOX_CONTAINER: Code execution capability
Recommended:
  • LOG_ACTIONS: Audit trail for all actions

⚑ Risks

Security bypass pattern detected in: src/scanners/prompt-injection-detector.js critical

Mitigation: This skill attempts to disable security features. Do not use.

Hardcoded secrets detected in: docs/en/README.md, docs/fr/README.md, src/scanners/secrets-scanner.js high

Mitigation: Remove hardcoded secrets. Use environment variables instead.

Prompt injection patterns detected in: docs/en/README.md, docs/fr/README.md, README.md, src/index.js high

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

Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD, TOOL_ABUSE_SYSTEM_MODIFICATION critical

Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments

Command injection risk: MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL critical

Mitigation: Remove embedded script tags and encoded payloads.

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 β€” $5.00

🚨 Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

πŸ“„ Raw SSDS JSON click to expand
{
  "meta": {
    "document_id": "ssds:auto:openclaw-security-guard:1.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T03:36:52.585Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Openclaw Security Guard",
    "version": "1.0.0",
    "format": "agent_skill",
    "description": "Security audit CLI + live dashboard for OpenClaw. Scans for secrets, config issues, prompt injections, vulnerable dependencies, and unverified MCP servers. Zero telemetry.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "ed5cac7c6e92647521bc488a5f52b33235b627844c7d91f29be729db6daec887",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "admin",
      "can_install_deps": true,
      "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": false,
      "reads_credential_files": true,
      "reads_browser_data": true,
      "reads_keychain": false
    },
    "services": [],
    "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": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "CODE_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_FILES",
      "CREDS_BROWSER",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "SECURITY_BYPASS",
        "name": "Security Bypass",
        "description": "Attempts to disable security features in: src/scanners/prompt-injection-detector.js"
      },
      {
        "code": "HARDCODED_SECRET",
        "name": "Hardcoded Secrets",
        "description": "Contains hardcoded secrets/API keys in: docs/en/README.md, docs/fr/README.md, src/scanners/secrets-scanner.js"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: docs/en/README.md, docs/fr/README.md, README.md, src/index.js, src/scanners/prompt-injection-detector.js"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: docs/en/README.md, docs/fr/README.md"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: src/scanners/prompt-injection-detector.js"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: src/cli/index.js"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: src/dashboard/server.js"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD, TOOL_ABUSE_SYSTEM_MODIFICATION: Instructs agent to install external binary or package"
      },
      {
        "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": "MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL: Script tags, VBScript, or encoded script data URIs"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 10 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": "A1: Local side effects only",
      "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": "Security bypass pattern detected in: src/scanners/prompt-injection-detector.js",
        "severity": "critical",
        "mitigation": "This skill attempts to disable security features. Do not use."
      },
      {
        "risk": "Hardcoded secrets detected in: docs/en/README.md, docs/fr/README.md, src/scanners/secrets-scanner.js",
        "severity": "high",
        "mitigation": "Remove hardcoded secrets. Use environment variables instead."
      },
      {
        "risk": "Prompt injection patterns detected in: docs/en/README.md, docs/fr/README.md, README.md, src/index.js",
        "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, TOOL_ABUSE_SYSTEM_MODIFICATION",
        "severity": "critical",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL",
        "severity": "critical",
        "mitigation": "Remove embedded script tags and encoded payloads."
      },
      {
        "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": "docs/ar/README.md",
      "file_path": "docs/ar/README.md"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "docs/en/README.md",
      "file_path": "docs/en/README.md"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "docs/fr/README.md",
      "file_path": "docs/fr/README.md"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "docs/README.md",
      "file_path": "docs/README.md"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "package.json",
      "file_path": "package.json"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "src/cli/index.js",
      "file_path": "src/cli/index.js"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "src/dashboard/server.js",
      "file_path": "src/dashboard/server.js"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "src/hardening/auto-hardener.js",
      "file_path": "src/hardening/auto-hardener.js"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] docs/ar/README.md:53: npm install -g openclaw-security-guard",
      "file_path": "docs/ar/README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "INSTRUCTED_GIT_CLONE_AND_BUILD [MEDIUM] docs/ar/README.md:313: git clone https://github.com/2pidata/openclaw-security-guard.git",
      "file_path": "docs/ar/README.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_IGNORE_INSTRUCTIONS [HIGH] docs/en/README.md:439: 1. **Instruction Override** - \"ignore previous instructions\"",
      "file_path": "docs/en/README.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] docs/en/README.md:79: npm install -g openclaw-security-guard",
      "file_path": "docs/en/README.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "SECRET_PRIVATE_KEY [CRITICAL] docs/en/README.md:402: | Private Keys | `-----BEGIN RSA PRIVATE KEY-----` |",
      "file_path": "docs/en/README.md"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_IGNORE_INSTRUCTIONS [HIGH] docs/fr/README.md:348: 1. **Override d'Instructions** - \"ignore previous instructions\"",
      "file_path": "docs/fr/README.md"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] docs/fr/README.md:79: npm install -g openclaw-security-guard",
      "file_path": "docs/fr/README.md"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "SECRET_PRIVATE_KEY [CRITICAL] docs/fr/README.md:325: | ClΓ©s PrivΓ©es | `-----BEGIN RSA PRIVATE KEY-----` |",
      "file_path": "docs/fr/README.md"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_IGNORE_INSTRUCTIONS [HIGH] README.md:232: const check = await checkPromptInjection('ignore all previous instructions');",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:49: npm install -g openclaw-security-guard",
      "file_path": "README.md"
    }
  ]
}