Tork Guardian

· v1.0.2

High Risk

AI governance and security layer for OpenClaw agents. Intentionally inspects AI agent traffic to detect PII leaks, policy violations, and dangerous tool calls.

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

⚠️ Hazard Flags

EXEC CODE_EXEC 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 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

SSH key access patterns in: dist/config.js, README.md, SKILL.md, src/config.ts, tests/interceptors/tool.test.ts high

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

Cloud credential access patterns in: dist/config.js, README.md, SKILL.md, src/config.ts high

Mitigation: Verify legitimate need for cloud credential access.

Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION critical

Mitigation: Remove system modification commands

Command injection risk: COMMAND_INJECTION_EVAL, MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM critical

Mitigation: Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD high

Mitigation: Document all external data transfers. Remove suspicious upload references.

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:@torknetwork/guardian:1.0.2",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T03:24:34.760Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Tork Guardian",
    "version": "1.0.2",
    "format": "agent_skill",
    "description": "AI governance and security layer for OpenClaw agents. Intentionally inspects AI agent traffic to detect PII leaks, policy violations, and dangerous tool calls.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "a56f3d0bb50855e8330c5dd234601c6ebc47c9dcb4b03a1995cdccf77dfbb110",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "user",
      "can_install_deps": true,
      "can_persist": false
    },
    "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": "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",
      "CODE_EXEC",
      "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",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: dist/config.js, README.md, SKILL.md, src/config.ts, tests/interceptors/tool.test.ts"
      },
      {
        "code": "CRED_CLOUD",
        "name": "Cloud Credential Access",
        "description": "Accesses cloud credentials (AWS/GCP/Azure) in: dist/config.js, README.md, SKILL.md, src/config.ts"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: dist/scanner/rules.js"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: dist/config.js, dist/scanner/api.js, README.md, SKILL.md, src/config.ts, src/scanner/api.ts, tests/config.test.ts, tests/interceptors/tool.test.ts"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: dist/scanner/rules.js, tests/scanner/index.test.ts"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION: 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_EVAL, MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM: Dangerous code execution functions that can execute arbitrary code"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "MCP_EXFIL_EXTERNAL_UPLOAD: Description mentions uploading data to external servers"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 9 security patterns (28 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": "SSH key access patterns in: dist/config.js, README.md, SKILL.md, src/config.ts, tests/interceptors/tool.test.ts",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Cloud credential access patterns in: dist/config.js, README.md, SKILL.md, src/config.ts",
        "severity": "high",
        "mitigation": "Verify legitimate need for cloud credential access."
      },
      {
        "risk": "Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PERMISSION_MANIPULATION",
        "severity": "critical",
        "mitigation": "Remove system modification commands"
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_EVAL, MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM",
        "severity": "critical",
        "mitigation": "Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD",
        "severity": "high",
        "mitigation": "Document all external data transfers. Remove suspicious upload references."
      }
    ],
    "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": "dist/client.js",
      "file_path": "dist/client.js"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "dist/config.js",
      "file_path": "dist/config.js"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "dist/examples/development.js",
      "file_path": "dist/examples/development.js"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "dist/examples/enterprise.js",
      "file_path": "dist/examples/enterprise.js"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "dist/examples/index.js",
      "file_path": "dist/examples/index.js"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "dist/examples/minimal.js",
      "file_path": "dist/examples/minimal.js"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "dist/examples/production.js",
      "file_path": "dist/examples/production.js"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "dist/handlers/network-access.js",
      "file_path": "dist/handlers/network-access.js"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "dist/index.js",
      "file_path": "dist/index.js"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "dist/interceptors/llm.js",
      "file_path": "dist/interceptors/llm.js"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] dist/config.js:14: 'chmod 777',",
      "file_path": "dist/config.js"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] dist/config.js:11: 'rm -rf',",
      "file_path": "dist/config.js"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SYS_PERMISSION_MANIPULATION [CRITICAL] dist/config.js:14: 'chmod 777',",
      "file_path": "dist/config.js"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_EVAL [CRITICAL] dist/scanner/index.js:84: const match = pattern.exec(line);",
      "file_path": "dist/scanner/index.js"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_EVAL [CRITICAL] dist/scanner/rules.js:8: name: 'eval() usage',",
      "file_path": "dist/scanner/rules.js"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] README.md:153: 'rm -rf', 'mkfs', 'dd if=', 'chmod 777',",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_EXFIL_EXTERNAL_UPLOAD [HIGH] README.md:169: blockedDomains: ['evil.com'],            // Domains always blocked",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] README.md:33: args: { command: 'rm -rf /' },",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SYS_PERMISSION_MANIPULATION [CRITICAL] README.md:153: 'rm -rf', 'mkfs', 'dd if=', 'chmod 777',",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] SKILL.md:153: 'rm -rf', 'mkfs', 'dd if=', 'chmod 777',",
      "file_path": "SKILL.md"
    }
  ]
}