High Risk
One layer in a multi-layer security stack for OpenClaw agents. Intercepts prompt injection, exfiltration attempts, tool abuse, and social engineering before they reach the model. Use alongside OpenClaw's built-in capability restrictions for defense-in-depth.
H:4 D:4 A:4 C:1
⚠️ Hazard Flags
EXEC PERSISTENCE FS_READ_WORKSPACE FS_READ_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES ACT_PURCHASE 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:
- APPROVE_PURCHASE: Financial actions possible
- SANDBOX_CONTAINER: Code execution capability
Recommended:
- LOG_ACTIONS: Audit trail for all actions
⚡ Risks
Cloud credential access patterns in: scripts/runtime_monitor.py, scripts/egress_scanner.py high
Mitigation: Verify legitimate need for cloud credential access.
Prompt injection patterns detected in: scripts/onboard.py high
Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.
Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP high
Mitigation: Add proper exit conditions or limits to loops
Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS high
Mitigation: Avoid accessing system directories unless absolutely necessary.
Command injection risk: SQL_INJECTION_STRING_FORMAT, MCP_SQL_BLIND, COMMAND_INJECTION_EVAL critical
Mitigation: Use parameterized queries with ? or %s placeholders
Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low
Mitigation: Provide clear, detailed description of skill functionality
Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS high
Mitigation: Do not access credential files or sensitive system files
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:clawguardian:2.4.5",
"ssds_version": "0.2.0",
"scanner_version": "0.4.0+fe6fd9123d50",
"created_at": "2026-03-08T13:09:59.533Z",
"created_by": {
"agent": "safeagentskills-cli/generate-ssds"
},
"language": "en",
"notes": "Auto-generated SSDS. Manual review recommended."
},
"skill": {
"name": "Guardian",
"version": "2.4.5",
"format": "agent_skill",
"description": "One layer in a multi-layer security stack for OpenClaw agents. Intercepts prompt injection, exfiltration attempts, tool abuse, and social engineering before they reach the model. Use alongside OpenClaw's built-in capability restrictions for defense-in-depth.",
"publisher": "ClawHub",
"source": {
"channel": "clawhub",
"slug": "guardian",
"owner": "bluemax30001",
"downloads": 668,
"stars": 1
},
"artifact": {
"sha256": "a29e0469e1147c89b59ef989bbd94f7f75bda67446bfde5231048a1cf0cd58e9",
"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": false,
"writes_user_home": false,
"writes_system": false,
"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": [],
"actions": {
"can_send_messages": false,
"can_post_public": false,
"can_purchase": true,
"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": 4,
"C": 1
},
"flags": [
"EXEC",
"PERSISTENCE",
"FS_READ_WORKSPACE",
"FS_READ_USER",
"FS_DELETE",
"NET_EGRESS_ANY",
"CREDS_ENV",
"CREDS_FILES",
"ACT_PURCHASE",
"PI_WEB",
"PI_DOCUMENTS"
],
"custom_flags": [
{
"code": "CRED_CLOUD",
"name": "Cloud Credential Access",
"description": "Accesses cloud credentials (AWS/GCP/Azure) in: scripts/runtime_monitor.py, scripts/egress_scanner.py"
},
{
"code": "PROMPT_INJECTION",
"name": "Prompt Injection Risk",
"description": "Contains prompt injection patterns in: scripts/onboard.py, scripts/guardian.py, core/context_modifiers.py"
},
{
"code": "PERSISTENCE",
"name": "Persistence Mechanism",
"description": "Creates scheduled tasks or startup entries in: scripts/onboard.py, scripts/local_audit.py, scripts/daily_digest.py"
},
{
"code": "FILE_DELETE",
"name": "File Deletion",
"description": "Can delete files in: scripts/noc-guardian-threats.py, scripts/noc-email-collector.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: 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": "SQL_INJECTION_STRING_FORMAT, MCP_SQL_BLIND, COMMAND_INJECTION_EVAL: SQL query with string formatting (SQL injection risk)"
},
{
"code": "DATA_EXFILTRATION",
"name": "Data Exfiltration Risk",
"description": "DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS: Accessing sensitive system or credential files"
}
],
"confidence": {
"level": "medium",
"basis": [
"static_analysis"
],
"notes": "Detected 9 security patterns (26 vendored rule hits). Review recommended."
},
"rationale": {
"H": "H4: Critical: Privilege escalation or malware detected",
"D": "D4: Critical: Credential theft or data exfiltration",
"A": "A4: External actions (deploy/message/post)",
"C": "C1: General content"
}
},
"containment": {
"level": "maximum",
"required": [
{
"control": "APPROVE_PURCHASE",
"reason": "Financial actions possible"
},
{
"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": "Cloud credential access patterns in: scripts/runtime_monitor.py, scripts/egress_scanner.py",
"severity": "high",
"mitigation": "Verify legitimate need for cloud credential access."
},
{
"risk": "Prompt injection patterns detected in: scripts/onboard.py",
"severity": "high",
"mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
},
{
"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",
"severity": "high",
"mitigation": "Avoid accessing system directories unless absolutely necessary."
},
{
"risk": "Command injection risk: SQL_INJECTION_STRING_FORMAT, MCP_SQL_BLIND, COMMAND_INJECTION_EVAL",
"severity": "critical",
"mitigation": "Use parameterized queries with ? or %s placeholders"
},
{
"risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
"severity": "low",
"mitigation": "Provide clear, detailed description of skill functionality"
},
{
"risk": "Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS",
"severity": "high",
"mitigation": "Do not access credential files or sensitive system files"
}
],
"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": "SKILL.md",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:file-2",
"type": "file_excerpt",
"title": "scripts/telegram_notify.py",
"file_path": "scripts/telegram_notify.py"
},
{
"evidence_id": "EV:file-3",
"type": "file_excerpt",
"title": "scripts/serve.py",
"file_path": "scripts/serve.py"
},
{
"evidence_id": "EV:file-4",
"type": "file_excerpt",
"title": "scripts/runtime_monitor.py",
"file_path": "scripts/runtime_monitor.py"
},
{
"evidence_id": "EV:file-5",
"type": "file_excerpt",
"title": "scripts/README.md",
"file_path": "scripts/README.md"
},
{
"evidence_id": "EV:file-6",
"type": "file_excerpt",
"title": "scripts/primary_notify_local.py",
"file_path": "scripts/primary_notify_local.py"
},
{
"evidence_id": "EV:file-7",
"type": "file_excerpt",
"title": "scripts/pre_publish_check.py",
"file_path": "scripts/pre_publish_check.py"
},
{
"evidence_id": "EV:file-8",
"type": "file_excerpt",
"title": "scripts/onboard.py",
"file_path": "scripts/onboard.py"
},
{
"evidence_id": "EV:file-9",
"type": "file_excerpt",
"title": "scripts/noc-guardian-threats.py",
"file_path": "scripts/noc-guardian-threats.py"
},
{
"evidence_id": "EV:file-10",
"type": "file_excerpt",
"title": "scripts/noc-email-collector.py",
"file_path": "scripts/noc-email-collector.py"
},
{
"evidence_id": "EV:cisco-1",
"type": "file_excerpt",
"title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:cisco-2",
"type": "file_excerpt",
"title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] scripts/serve.py:23: DEFAULT_CONFIG_PATH = Path(os.environ.get(\"GUARDIAN_CONFIG\") or (SKILL_ROOT / \"c",
"file_path": "scripts/serve.py"
},
{
"evidence_id": "EV:cisco-3",
"type": "file_excerpt",
"title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] scripts/runtime_monitor.py:154: sql = f\"SELECT {', '.join(select_parts)} FROM {table}\"",
"file_path": "scripts/runtime_monitor.py"
},
{
"evidence_id": "EV:cisco-4",
"type": "file_excerpt",
"title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] scripts/runtime_monitor.py:39: workspace = Path(os.environ.get(\"GUARDIAN_WORKSPACE\", os.getcwd())).expanduser()",
"file_path": "scripts/runtime_monitor.py"
},
{
"evidence_id": "EV:cisco-5",
"type": "file_excerpt",
"title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] scripts/noc-guardian-threats.py:28: WORKSPACE = Path(os.environ.get(\"GUARDIAN_WORKSPACE\") or SKILL_ROOT.parents[1]).",
"file_path": "scripts/noc-guardian-threats.py"
},
{
"evidence_id": "EV:cisco-6",
"type": "file_excerpt",
"title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] scripts/noc-email-collector.py:22: WORKSPACE = Path(os.environ.get(\"GUARDIAN_WORKSPACE\") or SKILL_ROOT.parents[1]).",
"file_path": "scripts/noc-email-collector.py"
},
{
"evidence_id": "EV:cisco-7",
"type": "file_excerpt",
"title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/local_audit.py:17: import urllib.request",
"file_path": "scripts/local_audit.py"
},
{
"evidence_id": "EV:cisco-8",
"type": "file_excerpt",
"title": "RESOURCE_ABUSE_INFINITE_LOOP [HIGH] scripts/guardian.py:409: while True:",
"file_path": "scripts/guardian.py"
},
{
"evidence_id": "EV:cisco-9",
"type": "file_excerpt",
"title": "MCP_SQL_BLIND [HIGH] scripts/guardian.py:440: time.sleep(max(1, int(interval)))",
"file_path": "scripts/guardian.py"
},
{
"evidence_id": "EV:cisco-10",
"type": "file_excerpt",
"title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] scripts/egress_scanner.py:131: sql = f\"SELECT {', '.join(select_parts)} FROM {table}\"",
"file_path": "scripts/egress_scanner.py"
}
]
}