Openclaw Rescue Kit
· v1.9.4
OpenClaw 自救套件 - 网关启动包装(端口冲突防护)、看门狗监控、自动重启、配置回滚、安全加固、日志清理、Git版本管理。当用户提到 OpenClaw 网关崩溃、需要看门狗、配置回滚、安全扫描、日志清理、端口冲突、或部署自救脚本时使用此技能。包含 10 个独立脚本和完整部署指南。
H:4 D:3 A:3 C:1
⚠️ Hazard Flags
EXEC PRIVILEGED PERSISTENCE NET_EGRESS_ANY CREDS_ENV ACT_SEND_MESSAGE PI_WEB
📋 Capabilities
Execution
- ✅ Shell execution
- ❌ Code execution
- ❌ Install dependencies
- ✅ Persistence
- Privilege: admin
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:
- APPROVE_SEND: Can send messages
- SANDBOX_CONTAINER: Code execution capability
Recommended:
- LOG_ACTIONS: Audit trail for all actions
⚡ Risks
Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PRIVILEGE_ESCALATION critical
Mitigation: Avoid accessing system directories unless absolutely necessary.
Command injection risk: TIRITH_DOTFILE_OVERWRITE, COMMAND_INJECTION_USER_INPUT high
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 — $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:openclaw-rescue-kit:1.9.4",
"ssds_version": "0.2.0",
"scanner_version": "0.4.0+fe6fd9123d50",
"created_at": "2026-03-06T19:49:07.283Z",
"created_by": {
"agent": "safeagentskills-cli/generate-ssds"
},
"language": "en",
"notes": "Auto-generated SSDS. Manual review recommended."
},
"skill": {
"name": "Openclaw Rescue Kit",
"version": "1.9.4",
"format": "agent_skill",
"description": "OpenClaw 自救套件 - 网关启动包装(端口冲突防护)、看门狗监控、自动重启、配置回滚、安全加固、日志清理、Git版本管理。当用户提到 OpenClaw 网关崩溃、需要看门狗、配置回滚、安全扫描、日志清理、端口冲突、或部署自救脚本时使用此技能。包含 10 个独立脚本和完整部署指南。",
"publisher": "unknown",
"source": {
"channel": "local"
},
"artifact": {
"sha256": "751a142f5bf04c96ba9cccf1af114f5c50b456356ea7f09c32bfcef14f044f2c",
"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": false,
"reads_user_home": false,
"reads_system": false,
"writes_workspace": false,
"writes_user_home": false,
"writes_system": false,
"can_delete": false
},
"network": {
"egress": "any",
"ingress": false
},
"credentials": {
"reads_env_vars": true,
"reads_credential_files": false,
"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": 3,
"A": 3,
"C": 1
},
"flags": [
"EXEC",
"PRIVILEGED",
"PERSISTENCE",
"NET_EGRESS_ANY",
"CREDS_ENV",
"ACT_SEND_MESSAGE",
"PI_WEB"
],
"custom_flags": [
{
"code": "PERSISTENCE",
"name": "Persistence Mechanism",
"description": "Creates scheduled tasks or startup entries in: README.md, scripts/install-rescue-kit.sh, SKILL.md, scripts/core.sh, scripts/security-hardening.sh, scripts/config-rollback.sh, scripts/gateway-watchdog.sh"
},
{
"code": "PRIVILEGE_ESCALATION",
"name": "Privilege Escalation",
"description": "Uses elevated privileges (sudo/root) in: scripts/install-rescue-kit.sh, scripts/security-hardening.sh"
},
{
"code": "TOOL_ABUSE",
"name": "Unauthorized Tool Use",
"description": "MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PRIVILEGE_ESCALATION: Access to critical system directories"
},
{
"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": "TIRITH_DOTFILE_OVERWRITE, COMMAND_INJECTION_USER_INPUT: Redirecting output to home directory dotfiles (shell config, SSH keys, etc.)"
}
],
"confidence": {
"level": "medium",
"basis": [
"static_analysis"
],
"notes": "Detected 5 security patterns (25 vendored rule hits). Review recommended."
},
"rationale": {
"H": "H4: Critical: Privilege escalation or malware detected",
"D": "D3: Credential access detected",
"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": "Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_PRIVILEGE_ESCALATION",
"severity": "critical",
"mitigation": "Avoid accessing system directories unless absolutely necessary."
},
{
"risk": "Command injection risk: TIRITH_DOTFILE_OVERWRITE, COMMAND_INJECTION_USER_INPUT",
"severity": "high"
},
{
"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": "README.md",
"file_path": "README.md"
},
{
"evidence_id": "EV:file-2",
"type": "file_excerpt",
"title": "scripts/config-rollback.sh",
"file_path": "scripts/config-rollback.sh"
},
{
"evidence_id": "EV:file-3",
"type": "file_excerpt",
"title": "scripts/core.sh",
"file_path": "scripts/core.sh"
},
{
"evidence_id": "EV:file-4",
"type": "file_excerpt",
"title": "scripts/gateway-start.sh",
"file_path": "scripts/gateway-start.sh"
},
{
"evidence_id": "EV:file-5",
"type": "file_excerpt",
"title": "scripts/gateway-watchdog.sh",
"file_path": "scripts/gateway-watchdog.sh"
},
{
"evidence_id": "EV:file-6",
"type": "file_excerpt",
"title": "scripts/git-tag.sh",
"file_path": "scripts/git-tag.sh"
},
{
"evidence_id": "EV:file-7",
"type": "file_excerpt",
"title": "scripts/health-check.sh",
"file_path": "scripts/health-check.sh"
},
{
"evidence_id": "EV:file-8",
"type": "file_excerpt",
"title": "scripts/install-rescue-kit.sh",
"file_path": "scripts/install-rescue-kit.sh"
},
{
"evidence_id": "EV:file-9",
"type": "file_excerpt",
"title": "scripts/log-cleaner.sh",
"file_path": "scripts/log-cleaner.sh"
},
{
"evidence_id": "EV:file-10",
"type": "file_excerpt",
"title": "scripts/notify.sh",
"file_path": "scripts/notify.sh"
},
{
"evidence_id": "EV:cisco-1",
"type": "file_excerpt",
"title": "TIRITH_DOTFILE_OVERWRITE [HIGH] README.md:81: * * * * * /bin/bash $HOME/.openclaw/scripts/gateway-watchdog.sh >> $HOME/.opencl",
"file_path": "README.md"
},
{
"evidence_id": "EV:cisco-2",
"type": "file_excerpt",
"title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/config-rollback.sh:350: local size=$(du -h \"$backup\" 2>/dev/null | awk '{print $1}')",
"file_path": "scripts/config-rollback.sh"
},
{
"evidence_id": "EV:cisco-3",
"type": "file_excerpt",
"title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/config-rollback.sh:1: #!/bin/bash",
"file_path": "scripts/config-rollback.sh"
},
{
"evidence_id": "EV:cisco-4",
"type": "file_excerpt",
"title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/core.sh:1: #!/bin/bash",
"file_path": "scripts/core.sh"
},
{
"evidence_id": "EV:cisco-5",
"type": "file_excerpt",
"title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/gateway-start.sh:29: pids=$(netstat -tlnp 2>/dev/null | grep \":$port \" | awk '{print $7}' | cut -d/ -",
"file_path": "scripts/gateway-start.sh"
},
{
"evidence_id": "EV:cisco-6",
"type": "file_excerpt",
"title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/gateway-start.sh:1: #!/bin/bash",
"file_path": "scripts/gateway-start.sh"
},
{
"evidence_id": "EV:cisco-7",
"type": "file_excerpt",
"title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/gateway-watchdog.sh:1: #!/bin/bash",
"file_path": "scripts/gateway-watchdog.sh"
},
{
"evidence_id": "EV:cisco-8",
"type": "file_excerpt",
"title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/git-tag.sh:18: 用法: $(basename \"$0\") <命令> [选项]",
"file_path": "scripts/git-tag.sh"
},
{
"evidence_id": "EV:cisco-9",
"type": "file_excerpt",
"title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/git-tag.sh:1: #!/bin/bash",
"file_path": "scripts/git-tag.sh"
},
{
"evidence_id": "EV:cisco-10",
"type": "file_excerpt",
"title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/health-check.sh:171: usage=$(free | awk 'NR==2{printf \"%.0f\", $3*100/$2}')",
"file_path": "scripts/health-check.sh"
}
]
}