๐Ÿ›ก๏ธ SafeAgentSkills

ClawAPI Manager

ยท v1.1.2

High Risk

OpenClaw API management and cost optimization. Manages multi-provider keys, monitors costs, routes tasks intelligently, and provides automated failover. Use when managing API keys, tracking costs, or optimizing API spending. Triggers: "api key", "cost", "budget", "provider", "validate config", "fix config".

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

โš ๏ธ Hazard Flags

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

๐Ÿ“‹ Capabilities

Execution

  • โœ… Shell execution
  • โŒ Code execution
  • โŒ Install dependencies
  • โœ… Persistence
  • Privilege: user

Filesystem

  • โœ… Read workspace
  • โœ… Write workspace
  • โœ… Read home
  • โœ… Write home
  • โŒ Read system
  • โœ… Delete

Network

  • Egress: any
  • โŒ Ingress

Credentials

  • โœ… Environment vars
  • โœ… Credential files
  • โŒ Browser data
  • โŒ Keychain

Actions

โœ… send messagesโŒ post publicโŒ purchaseโŒ transfer moneyโŒ deployโŒ delete external

๐Ÿ”’ Containment

Level: maximum

Required:
  • APPROVE_SEND: Can send messages
  • SANDBOX_CONTAINER: Code execution capability
Recommended:
  • LOG_ACTIONS: Audit trail for all actions

โšก Risks

Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP high

Mitigation: Add proper exit conditions or limits to loops

Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD critical

Mitigation: Avoid accessing system directories unless absolutely necessary.

Command injection risk: MCP_SQL_BLIND, COMMAND_INJECTION_USER_INPUT high

Mitigation: Remove SQL exploitation patterns.

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_ENV_VARS, DATA_EXFIL_SENSITIVE_FILES critical

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.

๐Ÿง  Deep Analysis โ€” $5.00

๐Ÿšจ Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

๐Ÿ“„ Raw SSDS JSON click to expand
{
  "meta": {
    "document_id": "ssds:auto:clawapi-manager:1.1.2",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T15:49:48.267Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "ClawAPI Manager",
    "version": "1.1.2",
    "format": "agent_skill",
    "description": "OpenClaw API management and cost optimization. Manages multi-provider keys, monitors costs, routes tasks intelligently, and provides automated failover. Use when managing API keys, tracking costs, or optimizing API spending. Triggers: \"api key\", \"cost\", \"budget\", \"provider\", \"validate config\", \"fix config\".",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "8c4b08833d22997272210df6fa4254db674fe7dedd9a7b092b22a6d05b0da965",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "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": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [
      {
        "service": "messaging",
        "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"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_WRITE_SYSTEM",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "ACT_SEND_MESSAGE",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: install.sh"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: lib/config_manager.py"
      },
      {
        "code": "RESOURCE_ABUSE",
        "name": "Resource Abuse Risk",
        "description": "RESOURCE_ABUSE_INFINITE_LOOP detected: Infinite loop without clear exit condition"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "MCP_SYS_CRITICAL_ACCESS, TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD: Access to critical system directories"
      },
      {
        "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: Blind SQL injection, system table access, or stored procedure abuse"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_ENV_VARS, DATA_EXFIL_SENSITIVE_FILES: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 7 security patterns (43 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": "Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP",
        "severity": "high",
        "mitigation": "Add proper exit conditions or limits to loops"
      },
      {
        "risk": "Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD",
        "severity": "critical",
        "mitigation": "Avoid accessing system directories unless absolutely necessary."
      },
      {
        "risk": "Command injection risk: MCP_SQL_BLIND, COMMAND_INJECTION_USER_INPUT",
        "severity": "high",
        "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: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_ENV_VARS, DATA_EXFIL_SENSITIVE_FILES",
        "severity": "critical",
        "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": "auto_rotate.sh",
      "file_path": "auto_rotate.sh"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "bypass_mode.sh",
      "file_path": "bypass_mode.sh"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "check_cost.sh",
      "file_path": "check_cost.sh"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "check_quota.sh",
      "file_path": "check_quota.sh"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "claw_api_manager_central.py",
      "file_path": "claw_api_manager_central.py"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "clawapi_helper.py",
      "file_path": "clawapi_helper.py"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "clawapi-rich.py",
      "file_path": "clawapi-rich.py"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "clawapi-tui.py",
      "file_path": "clawapi-tui.py"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "clawapi-ui.py",
      "file_path": "clawapi-ui.py"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "encrypt_keys.sh",
      "file_path": "encrypt_keys.sh"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] auto_rotate.sh:1: #!/bin/bash",
      "file_path": "auto_rotate.sh"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] bypass_mode.sh:1: #!/bin/bash",
      "file_path": "bypass_mode.sh"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] check_cost.sh:1: #!/bin/bash",
      "file_path": "check_cost.sh"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] check_quota.sh:1: #!/bin/bash",
      "file_path": "check_quota.sh"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "RESOURCE_ABUSE_INFINITE_LOOP [HIGH] clawapi-rich.py:130: while True:",
      "file_path": "clawapi-rich.py"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] clawapi-rich.py:164: time.sleep(0.5)",
      "file_path": "clawapi-rich.py"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] clawapi-ui.py:35: time.sleep(0.5)",
      "file_path": "clawapi-ui.py"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] encrypt_keys.sh:17: chmod 600 \"${KEY_FILE}\"",
      "file_path": "encrypt_keys.sh"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] encrypt_keys.sh:1: #!/bin/bash",
      "file_path": "encrypt_keys.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] install.sh:14: chmod 700 \"${SCRIPT_DIR}\"",
      "file_path": "install.sh"
    }
  ]
}