ClawAPI Manager
ยท v1.1.2
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".
โ ๏ธ Hazard Flags
๐ Capabilities
Execution
- โ Shell execution
- โ Code execution
- โ Install dependencies
- โ Persistence
- Privilege: user
Filesystem
- โ Read workspace
- โ Write workspace
- โ Read home
- โ Write home
- โ Read system
- โ Delete
Network
- Egress: any
- โ Ingress
Credentials
- โ Environment vars
- โ Credential files
- โ Browser data
- โ Keychain
Actions
๐ Containment
Level: maximum
- APPROVE_SEND: Can send messages
- SANDBOX_CONTAINER: Code execution capability
- LOG_ACTIONS: Audit trail for all actions
โก Risks
Mitigation: Add proper exit conditions or limits to loops
Mitigation: Avoid accessing system directories unless absolutely necessary.
Mitigation: Remove SQL exploitation patterns.
Mitigation: Provide clear, detailed description of skill functionality
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.
๐ง Deep Analysis โ $5.00๐จ Incident Response
Kill switch: Stop the agent process
Containment: Review logs for unexpected actions
Recovery: Depends on skill capabilities
๐ 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"
}
]
}