Lieutenant - AI Agent Security

· v1.0.0

Medium Risk

"AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifying external agents, or scanning untrusted content."

H:3 D:4 A:3 C:1

⚠️ Hazard Flags

FS_READ_WORKSPACE FS_READ_USER NET_EGRESS_ANY CREDS_ENV CREDS_FILES ACT_SEND_MESSAGE 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_SEND: Can send messages

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Prompt injection patterns detected in: scripts/scan.py, SKILL.md 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

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_HTTP_POST, DATA_EXFIL_ENV_VARS 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:lieutenant:1.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T03:16:26.927Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Lieutenant - AI Agent Security",
    "version": "1.0.0",
    "format": "agent_skill",
    "description": "\"AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifying external agents, or scanning untrusted content.\"",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "5c33ff975f0dc909d4cfed34681b839a2177ded7e4c2467245caedddf6ee0d6d",
      "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": true,
      "reads_user_home": true,
      "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": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [],
    "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",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 3,
      "D": 4,
      "A": 3,
      "C": 1
    },
    "flags": [
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "ACT_SEND_MESSAGE",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: scripts/scan.py, SKILL.md"
      },
      {
        "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": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_ENV_VARS: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 4 security patterns (14 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H3: Shell/code execution or persistence 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": "APPROVE_SEND",
        "reason": "Can send messages"
      }
    ],
    "recommended": [
      {
        "control": "LOG_ACTIONS",
        "reason": "Audit trail for all actions"
      }
    ],
    "uncontained_risk": "Risk level depends on manual review of actual capabilities."
  },
  "risks": {
    "risks": [
      {
        "risk": "Prompt injection patterns detected in: scripts/scan.py, SKILL.md",
        "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": "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_HTTP_POST, DATA_EXFIL_ENV_VARS",
        "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": "scripts/scan.py",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "scripts/verify_agent.py",
      "file_path": "scripts/verify_agent.py"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/scan.py:32: import requests",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_HTTP_POST [CRITICAL] scripts/scan.py:48: response = requests.post(",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] scripts/scan.py:34: api_key = os.environ.get(\"TRUSTAGENTS_API_KEY\")",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] scripts/scan.py:104: \"allow\": \"\\033[92m\",  # Green",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] scripts/scan.py:104: \"allow\": \"\\033[92m\",  # Green",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/verify_agent.py:24: import requests",
      "file_path": "scripts/verify_agent.py"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_HTTP_POST [CRITICAL] scripts/verify_agent.py:54: response = requests.post(",
      "file_path": "scripts/verify_agent.py"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] scripts/verify_agent.py:44: api_key = os.environ.get(\"TRUSTAGENTS_API_KEY\")",
      "file_path": "scripts/verify_agent.py"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] scripts/verify_agent.py:107: \"allow\": \"\\033[92m\",  # Green",
      "file_path": "scripts/verify_agent.py"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] scripts/verify_agent.py:107: \"allow\": \"\\033[92m\",  # Green",
      "file_path": "scripts/verify_agent.py"
    }
  ]
}