windows-ui-automation
ยท v1.0.0
Automate Windows GUI interactions (mouse, keyboard, windows) using PowerShell. Use when the user needs to simulate user input on the desktop, such as moving the cursor, clicking buttons, typing text in non-web apps, or managing window states.
H:4 D:0 A:0 C:1
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: none
- โ Ingress
Credentials
- โ Environment vars
- โ Credential files
- โ Browser data
- โ Keychain
Actions
โ send messagesโ post publicโ purchaseโ transfer moneyโ deployโ delete external
๐ Containment
Level: maximum
Recommended:
- LOG_ACTIONS: Audit trail for all actions
โก Risks
Command injection risk: MCP_CMD_DANGEROUS_SYSTEM, MCP_SCRIPT_TAGS critical
Mitigation: Remove dangerous system commands.
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.
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:windows-ui-automation:1.0.0",
"ssds_version": "0.2.0",
"scanner_version": "0.4.0+fe6fd9123d50",
"created_at": "2026-03-05T02:46:18.023Z",
"created_by": {
"agent": "safeagentskills-cli/generate-ssds"
},
"language": "en",
"notes": "Auto-generated SSDS. Manual review recommended."
},
"skill": {
"name": "windows-ui-automation",
"version": "1.0.0",
"format": "agent_skill",
"description": "Automate Windows GUI interactions (mouse, keyboard, windows) using PowerShell. Use when the user needs to simulate user input on the desktop, such as moving the cursor, clicking buttons, typing text in non-web apps, or managing window states.",
"publisher": "ClawHub",
"source": {
"channel": "local"
},
"artifact": {
"sha256": "472c391057f792d1a34157e7ab57e7135b77268c6632efe772b58924bc7ef17d",
"hash_method": "files_sorted"
}
},
"capabilities": {
"execution": {
"can_exec_shell": false,
"can_exec_code": false,
"privilege_level": "user",
"can_install_deps": false,
"can_persist": false
},
"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": "none",
"ingress": false
},
"credentials": {
"reads_env_vars": false,
"reads_credential_files": false,
"reads_browser_data": false,
"reads_keychain": false
},
"services": [],
"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": [],
"content_types": [
"general"
]
},
"hazards": {
"hdac": {
"H": 4,
"D": 0,
"A": 0,
"C": 1
},
"flags": [],
"custom_flags": [
{
"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": "MCP_CMD_DANGEROUS_SYSTEM, MCP_SCRIPT_TAGS: Dangerous system commands or Windows exploitation"
}
],
"confidence": {
"level": "medium",
"basis": [
"static_analysis"
],
"notes": "Detected 2 security patterns (3 vendored rule hits). Review recommended."
},
"rationale": {
"H": "H4: Critical: Privilege escalation or malware detected",
"D": "D0: No sensitive data access",
"A": "A0: No side effects detected",
"C": "C1: General content"
}
},
"containment": {
"level": "maximum",
"required": [],
"recommended": [
{
"control": "LOG_ACTIONS",
"reason": "Audit trail for all actions"
}
],
"uncontained_risk": "Risk level depends on manual review of actual capabilities."
},
"risks": {
"risks": [
{
"risk": "Command injection risk: MCP_CMD_DANGEROUS_SYSTEM, MCP_SCRIPT_TAGS",
"severity": "critical",
"mitigation": "Remove dangerous system commands."
},
{
"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": "SKILL.md",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:file-2",
"type": "file_excerpt",
"title": "_meta.json",
"file_path": "_meta.json"
},
{
"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": "MCP_CMD_DANGEROUS_SYSTEM [CRITICAL] SKILL.md:3: description: Automate Windows GUI interactions (mouse, keyboard, windows) using ",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:cisco-3",
"type": "file_excerpt",
"title": "MCP_SCRIPT_TAGS [HIGH] SKILL.md:49: $wshell = New-Object -ComObject WScript.Shell; $wshell.AppActivate(\"Notepad\")",
"file_path": "SKILL.md"
}
]
}