⚠️ Hazard Flags
EXEC PRIVILEGED 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_DELETE_EXTERNAL PI_WEB PI_DOCUMENTS
📋 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:
- SANDBOX_CONTAINER: Code execution capability
Recommended:
- LOG_ACTIONS: Audit trail for all actions
⚡ Risks
Code obfuscation detected in: scripts/erpclaw-os/generate_module.py medium
Mitigation: Deobfuscate and review code before use.
Prompt injection patterns detected in: scripts/erpclaw-payroll/db_query.py, scripts/erpclaw-os/tier_classifier.py, scripts/db_query.py high
Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.
Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD high
Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments
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_NETWORK_REQUESTS, DATA_EXFIL_BASE64_AND_NETWORK, 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.
🧠 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:erpclaw:3.4.2",
"ssds_version": "0.2.0",
"scanner_version": "0.4.0+fe6fd9123d50",
"created_at": "2026-03-28T09:33:46.838Z",
"created_by": {
"agent": "safeagentskills-cli/generate-ssds"
},
"language": "en",
"notes": "Auto-generated SSDS. Manual review recommended."
},
"skill": {
"name": "Erpclaw",
"version": "3.4.2",
"format": "agent_skill",
"description": ">",
"publisher": "ClawHub",
"source": {
"channel": "clawhub",
"slug": "erpclaw",
"owner": "mailnike",
"downloads": 263,
"stars": 0
},
"artifact": {
"sha256": "3376a08660dbe0934cb70defe5f1af0d0901cce30a5733e8268abfc314c2cfe4",
"hash_method": "files_sorted"
}
},
"capabilities": {
"execution": {
"can_exec_shell": true,
"can_exec_code": false,
"privilege_level": "admin",
"can_install_deps": false,
"can_persist": false
},
"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": [],
"actions": {
"can_send_messages": false,
"can_post_public": false,
"can_purchase": false,
"can_transfer_money": false,
"can_deploy": false,
"can_delete_external": true
},
"prompt_injection_surfaces": [
"web",
"documents"
],
"content_types": [
"general"
]
},
"hazards": {
"hdac": {
"H": 4,
"D": 4,
"A": 3,
"C": 1
},
"flags": [
"EXEC",
"PRIVILEGED",
"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_DELETE_EXTERNAL",
"PI_WEB",
"PI_DOCUMENTS"
],
"custom_flags": [
{
"code": "OBFUSCATED_CODE",
"name": "Obfuscated Code",
"description": "Contains obfuscated code patterns in: scripts/erpclaw-os/generate_module.py"
},
{
"code": "PROMPT_INJECTION",
"name": "Prompt Injection Risk",
"description": "Contains prompt injection patterns in: scripts/erpclaw-payroll/db_query.py, scripts/erpclaw-os/tier_classifier.py, scripts/db_query.py"
},
{
"code": "PRIVILEGE_ESCALATION",
"name": "Privilege Escalation",
"description": "Uses elevated privileges (sudo/root) in: scripts/erpclaw-meta/db_query.py"
},
{
"code": "FILE_DELETE",
"name": "File Deletion",
"description": "Can delete files in: SKILL.md, scripts/module_manager.py, scripts/erpclaw-setup/db_query.py, scripts/erpclaw-os/validate_module.py, scripts/erpclaw-os/sandbox.py, scripts/db_query.py"
},
{
"code": "TOOL_ABUSE",
"name": "Unauthorized Tool Use",
"description": "INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD: Instructs agent to install external binary or package"
},
{
"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_NETWORK_REQUESTS, DATA_EXFIL_BASE64_AND_NETWORK, DATA_EXFIL_SENSITIVE_FILES: HTTP client library imports that enable external communication"
}
],
"confidence": {
"level": "medium",
"basis": [
"static_analysis"
],
"notes": "Detected 8 security patterns (34 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": "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": "Code obfuscation detected in: scripts/erpclaw-os/generate_module.py",
"severity": "medium",
"mitigation": "Deobfuscate and review code before use."
},
{
"risk": "Prompt injection patterns detected in: scripts/erpclaw-payroll/db_query.py, scripts/erpclaw-os/tier_classifier.py, scripts/db_query.py",
"severity": "high",
"mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
},
{
"risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD",
"severity": "high",
"mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
},
{
"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_NETWORK_REQUESTS, DATA_EXFIL_BASE64_AND_NETWORK, 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": "_meta.json",
"file_path": "_meta.json"
},
{
"evidence_id": "EV:file-2",
"type": "file_excerpt",
"title": "SKILL.md",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:file-3",
"type": "file_excerpt",
"title": "scripts/onboarding.py",
"file_path": "scripts/onboarding.py"
},
{
"evidence_id": "EV:file-4",
"type": "file_excerpt",
"title": "scripts/module_manager.py",
"file_path": "scripts/module_manager.py"
},
{
"evidence_id": "EV:file-5",
"type": "file_excerpt",
"title": "scripts/erpclaw-tax/db_query.py",
"file_path": "scripts/erpclaw-tax/db_query.py"
},
{
"evidence_id": "EV:file-6",
"type": "file_excerpt",
"title": "scripts/erpclaw-setup/migrations/001_registry_tables.py",
"file_path": "scripts/erpclaw-setup/migrations/001_registry_tables.py"
},
{
"evidence_id": "EV:file-7",
"type": "file_excerpt",
"title": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/utils.py",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/utils.py"
},
{
"evidence_id": "EV:file-8",
"type": "file_excerpt",
"title": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/terms.py",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/terms.py"
},
{
"evidence_id": "EV:file-9",
"type": "file_excerpt",
"title": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/queries.py",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/queries.py"
},
{
"evidence_id": "EV:file-10",
"type": "file_excerpt",
"title": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/pseudocolumns.py",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/pseudocolumns.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_NETWORK_REQUESTS [MEDIUM] scripts/module_manager.py:21: import urllib.request",
"file_path": "scripts/module_manager.py"
},
{
"evidence_id": "EV:cisco-3",
"type": "file_excerpt",
"title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/queries.py:2181: base_sql += f\" WHERE {self._wheres}\"",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/queries.py"
},
{
"evidence_id": "EV:cisco-4",
"type": "file_excerpt",
"title": "MCP_SQL_BLIND [HIGH] scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/functions.py:107: class Cast(Function):",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/vendor/pypika/functions.py"
},
{
"evidence_id": "EV:cisco-5",
"type": "file_excerpt",
"title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] scripts/erpclaw-setup/lib/erpclaw_lib/validation.py:143: row = conn.execute(f\"SELECT * FROM {table} WHERE id = ?\", (entity_id,)).fetchone",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/validation.py"
},
{
"evidence_id": "EV:cisco-6",
"type": "file_excerpt",
"title": "MCP_SQL_BLIND [HIGH] scripts/erpclaw-setup/lib/erpclaw_lib/stock_posting.py:119: AND CAST(remaining_qty AS REAL) > 0",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/stock_posting.py"
},
{
"evidence_id": "EV:cisco-7",
"type": "file_excerpt",
"title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] scripts/erpclaw-setup/lib/erpclaw_lib/pagination.py:54: count_query = f\"SELECT COUNT(*) as cnt FROM ({query})\"",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/pagination.py"
},
{
"evidence_id": "EV:cisco-8",
"type": "file_excerpt",
"title": "MCP_SQL_BLIND [HIGH] scripts/erpclaw-setup/lib/erpclaw_lib/db.py:48: Usage in SQL: decimal_sum(column) instead of SUM(CAST(column AS REAL))",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/db.py"
},
{
"evidence_id": "EV:cisco-9",
"type": "file_excerpt",
"title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] scripts/erpclaw-setup/lib/erpclaw_lib/custom_fields.py:211: f\"SELECT 1 FROM [{target_table}] WHERE id = ?\",",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/custom_fields.py"
},
{
"evidence_id": "EV:cisco-10",
"type": "file_excerpt",
"title": "DATA_EXFIL_BASE64_AND_NETWORK [CRITICAL] scripts/erpclaw-setup/lib/erpclaw_lib/crypto.py:223: encoded = base64.b64encode(iv + ciphertext).decode(\"ascii\")",
"file_path": "scripts/erpclaw-setup/lib/erpclaw_lib/crypto.py"
}
]
}