High Risk
Trust Infrastructure for AI Agents - Like SSL/TLS for agent-to-agent communication. 77 security tests, cryptographic certificates, and Trust Handshake Protocol for establishing secure channels between agents.
H:4 D:4 A:2 C:1
⚠️ Hazard Flags
EXEC CODE_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 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
Pipe-to-shell pattern detected (curl|bash) in: agentshield_tester.py critical
Mitigation: Do not execute. Review source for malicious intent.
SSH key access patterns in: agentshield_tester.py high
Mitigation: Verify legitimate need for SSH access. Consider sandboxing.
Cloud credential access patterns in: secret_scanner.py, output_dlp.py high
Mitigation: Verify legitimate need for cloud credential access.
Hardcoded secrets detected in: agentshield_tester.py high
Mitigation: Remove hardcoded secrets. Use environment variables instead.
Prompt injection patterns detected in: supply_chain_scanner.py, echoleak_test.py, agentshield_tester.py, input_sanitizer.py high
Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.
Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION critical
Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments
Command injection risk: MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL critical
Mitigation: Remove embedded script tags and encoded payloads.
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_SENSITIVE_FILES, DATA_EXFIL_HTTP_POST, DATA_EXFIL_BASE64_AND_NETWORK 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:agentshield:1.0.25",
"ssds_version": "0.2.0",
"scanner_version": "0.4.0+fe6fd9123d50",
"created_at": "2026-03-28T09:28:14.278Z",
"created_by": {
"agent": "safeagentskills-cli/generate-ssds"
},
"language": "en",
"notes": "Auto-generated SSDS. Manual review recommended."
},
"skill": {
"name": "Agentshield Audit",
"version": "1.0.25",
"format": "agent_skill",
"description": "Trust Infrastructure for AI Agents - Like SSL/TLS for agent-to-agent communication. 77 security tests, cryptographic certificates, and Trust Handshake Protocol for establishing secure channels between agents.",
"publisher": "ClawHub",
"source": {
"channel": "clawhub",
"slug": "agentshield-audit",
"owner": "bartelmost",
"downloads": 365,
"stars": 0
},
"artifact": {
"sha256": "b13596993b0ba517fc953473ea5546840ce45d28e6bf26933d4ed167275e47ce",
"hash_method": "files_sorted"
}
},
"capabilities": {
"execution": {
"can_exec_shell": true,
"can_exec_code": true,
"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": [
{
"service": "email",
"operations": [
"read",
"write"
]
},
{
"service": "code_hosting",
"operations": [
"read",
"write"
]
}
],
"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": [
"web",
"documents"
],
"content_types": [
"general"
]
},
"hazards": {
"hdac": {
"H": 4,
"D": 4,
"A": 2,
"C": 1
},
"flags": [
"EXEC",
"CODE_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",
"PI_WEB",
"PI_DOCUMENTS"
],
"custom_flags": [
{
"code": "PIPE_TO_SHELL",
"name": "Pipe to Shell",
"description": "Downloads and executes remote code (curl|bash pattern) in: agentshield_tester.py"
},
{
"code": "CRED_SSH",
"name": "SSH Key Access",
"description": "Accesses SSH keys in: agentshield_tester.py"
},
{
"code": "CRED_CLOUD",
"name": "Cloud Credential Access",
"description": "Accesses cloud credentials (AWS/GCP/Azure) in: secret_scanner.py, output_dlp.py"
},
{
"code": "HARDCODED_SECRET",
"name": "Hardcoded Secrets",
"description": "Contains hardcoded secrets/API keys in: agentshield_tester.py"
},
{
"code": "PROMPT_INJECTION",
"name": "Prompt Injection Risk",
"description": "Contains prompt injection patterns in: supply_chain_scanner.py, echoleak_test.py, agentshield_tester.py, tool_sandbox.py"
},
{
"code": "HIDDEN_INSTRUCTIONS",
"name": "Hidden Instructions",
"description": "Contains hidden instructions in comments/invisible chars in: input_sanitizer.py, echoleak_test.py, README.md"
},
{
"code": "PRIVILEGE_ESCALATION",
"name": "Privilege Escalation",
"description": "Uses elevated privileges (sudo/root) in: agentshield_tester.py"
},
{
"code": "FILE_DELETE",
"name": "File Deletion",
"description": "Can delete files in: agentshield_tester.py"
},
{
"code": "TOOL_ABUSE",
"name": "Unauthorized Tool Use",
"description": "INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION: 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": "MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL: Script tags, VBScript, or encoded script data URIs"
},
{
"code": "DATA_EXFILTRATION",
"name": "Data Exfiltration Risk",
"description": "DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_SENSITIVE_FILES, DATA_EXFIL_HTTP_POST, DATA_EXFIL_BASE64_AND_NETWORK: HTTP client library imports that enable external communication"
}
],
"confidence": {
"level": "medium",
"basis": [
"static_analysis"
],
"notes": "Detected 12 security patterns (20 vendored rule hits). Review recommended."
},
"rationale": {
"H": "H4: Critical: Privilege escalation or malware detected",
"D": "D4: Critical: Credential theft or data exfiltration",
"A": "A2: Service integrations detected",
"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": "Pipe-to-shell pattern detected (curl|bash) in: agentshield_tester.py",
"severity": "critical",
"mitigation": "Do not execute. Review source for malicious intent."
},
{
"risk": "SSH key access patterns in: agentshield_tester.py",
"severity": "high",
"mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
},
{
"risk": "Cloud credential access patterns in: secret_scanner.py, output_dlp.py",
"severity": "high",
"mitigation": "Verify legitimate need for cloud credential access."
},
{
"risk": "Hardcoded secrets detected in: agentshield_tester.py",
"severity": "high",
"mitigation": "Remove hardcoded secrets. Use environment variables instead."
},
{
"risk": "Prompt injection patterns detected in: supply_chain_scanner.py, echoleak_test.py, agentshield_tester.py, input_sanitizer.py",
"severity": "high",
"mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
},
{
"risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION",
"severity": "critical",
"mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
},
{
"risk": "Command injection risk: MCP_SCRIPT_TAGS, COMMAND_INJECTION_EVAL",
"severity": "critical",
"mitigation": "Remove embedded script tags and encoded payloads."
},
{
"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_SENSITIVE_FILES, DATA_EXFIL_HTTP_POST, DATA_EXFIL_BASE64_AND_NETWORK",
"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": "verify_peer.py",
"file_path": "verify_peer.py"
},
{
"evidence_id": "EV:file-2",
"type": "file_excerpt",
"title": "verify_bundle.py",
"file_path": "verify_bundle.py"
},
{
"evidence_id": "EV:file-3",
"type": "file_excerpt",
"title": "tool_sandbox.py",
"file_path": "tool_sandbox.py"
},
{
"evidence_id": "EV:file-4",
"type": "file_excerpt",
"title": "supply_chain_scanner.py",
"file_path": "supply_chain_scanner.py"
},
{
"evidence_id": "EV:file-5",
"type": "file_excerpt",
"title": "SKILL.md",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:file-6",
"type": "file_excerpt",
"title": "show_certificate.py",
"file_path": "show_certificate.py"
},
{
"evidence_id": "EV:file-7",
"type": "file_excerpt",
"title": "setup.py",
"file_path": "setup.py"
},
{
"evidence_id": "EV:file-8",
"type": "file_excerpt",
"title": "secret_scanner.py",
"file_path": "secret_scanner.py"
},
{
"evidence_id": "EV:file-9",
"type": "file_excerpt",
"title": "README.md",
"file_path": "README.md"
},
{
"evidence_id": "EV:file-10",
"type": "file_excerpt",
"title": "output_dlp.py",
"file_path": "output_dlp.py"
},
{
"evidence_id": "EV:cisco-1",
"type": "file_excerpt",
"title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] verify_peer.py:96: import requests",
"file_path": "verify_peer.py"
},
{
"evidence_id": "EV:cisco-2",
"type": "file_excerpt",
"title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] verify_bundle.py:13: GREEN = \"\\033[92m\"",
"file_path": "verify_bundle.py"
},
{
"evidence_id": "EV:cisco-3",
"type": "file_excerpt",
"title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] verify_bundle.py:13: GREEN = \"\\033[92m\"",
"file_path": "verify_bundle.py"
},
{
"evidence_id": "EV:cisco-4",
"type": "file_excerpt",
"title": "MCP_SCRIPT_TAGS [HIGH] tool_sandbox.py:332: r'<script[^>]*>',",
"file_path": "tool_sandbox.py"
},
{
"evidence_id": "EV:cisco-5",
"type": "file_excerpt",
"title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] supply_chain_scanner.py:158: with open(filepath, 'rb') as f:",
"file_path": "supply_chain_scanner.py"
},
{
"evidence_id": "EV:cisco-6",
"type": "file_excerpt",
"title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
"file_path": "SKILL.md"
},
{
"evidence_id": "EV:cisco-7",
"type": "file_excerpt",
"title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:242: pip install -r requirements.txt",
"file_path": "README.md"
},
{
"evidence_id": "EV:cisco-8",
"type": "file_excerpt",
"title": "MCP_SCRIPT_TAGS [HIGH] input_sanitizer.py:74: (r'<script[^>]*>', ThreatLevel.CRITICAL),",
"file_path": "input_sanitizer.py"
},
{
"evidence_id": "EV:cisco-9",
"type": "file_excerpt",
"title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] initiate_audit.py:249: import requests",
"file_path": "initiate_audit.py"
},
{
"evidence_id": "EV:cisco-10",
"type": "file_excerpt",
"title": "DATA_EXFIL_HTTP_POST [CRITICAL] initiate_audit.py:264: response = requests.post(",
"file_path": "initiate_audit.py"
}
]
}