AgentMail sending and receiving with Python scripts

· v1.0.0

High Risk

python files which are used to send an email and to download received emails from an inbox. The email provider is agentmail.to, which offers an API. This way of email handling is very AI-agent friendly.

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

⚠️ Hazard Flags

EXEC FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES PI_WEB

📋 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:

SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP high

Mitigation: Add proper exit conditions or limits to loops

Unauthorized tool use: INSTRUCTED_BINARY_INSTALL high

Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments

Command injection risk: TIRITH_DOTFILE_OVERWRITE high

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: DATA_EXFIL_ENV_VARS medium

Mitigation: Minimize access to environment variables

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:python-agentmail-send-receive:1.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-07T07:31:17.188Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "AgentMail sending and receiving with Python scripts",
    "version": "1.0.0",
    "format": "agent_skill",
    "description": "python files which are used to send an email and to download received emails from an inbox. The email provider is agentmail.to, which offers an API. This way of email handling is very AI-agent friendly.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "a469ea447de754ba5196676608c213aea316967d85fed9c370a6dcc098f42bb6",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "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": true,
      "writes_user_home": true,
      "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": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": false
    },
    "prompt_injection_surfaces": [
      "web"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: check_mail.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": "INSTRUCTED_BINARY_INSTALL: 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": "TIRITH_DOTFILE_OVERWRITE: Redirecting output to home directory dotfiles (shell config, SSH keys, etc.)"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_ENV_VARS: Reading environment variables that may contain secrets"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 6 security patterns (6 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A1: Local side effects only",
      "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": "Resource abuse detected: RESOURCE_ABUSE_INFINITE_LOOP",
        "severity": "high",
        "mitigation": "Add proper exit conditions or limits to loops"
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL",
        "severity": "high",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: TIRITH_DOTFILE_OVERWRITE",
        "severity": "high"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: DATA_EXFIL_ENV_VARS",
        "severity": "medium",
        "mitigation": "Minimize access to environment variables"
      }
    ],
    "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": "check_mail.py",
      "file_path": "check_mail.py"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "send_email.py",
      "file_path": "send_email.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_ENV_VARS [MEDIUM] check_mail.py:77: api_key = os.getenv(\"AGENTMAIL_API_KEY\")",
      "file_path": "check_mail.py"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "RESOURCE_ABUSE_INFINITE_LOOP [HIGH] check_mail.py:59: while True:",
      "file_path": "check_mail.py"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] send_email.py:7: client = AgentMail(api_key=os.getenv(\"AGENTMAIL_API_KEY\"))",
      "file_path": "send_email.py"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:34: uv pip install --python venv/bin/python agentmail python-dotenv",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "TIRITH_DOTFILE_OVERWRITE [HIGH] SKILL.md:44: cat > ~/.openclaw/workspace/agentmail/.env << 'EOF'",
      "file_path": "SKILL.md"
    }
  ]
}