AgentCloak - Email Proxy that filters PII, 2FA, and password resets

· v1.0.0

Medium Risk

"Secure email proxy for AI agents. Search, read, and draft emails via MCP with server-side credential isolation, PII redaction, prompt injection detection, and content filtering. Unlike raw Gmail/IMAP skills, your agent never sees passwords or unfiltered content. Self-host or use the hosted version."

H:3 D:4 A:0 C:1

⚠️ Hazard Flags

NET_EGRESS_ANY CREDS_ENV 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

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Unauthorized tool use: INSTRUCTED_GIT_CLONE_AND_BUILD medium

Mitigation: Use pre-built packages or vendored dependencies instead of cloning repos

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_SENSITIVE_DATA, MCP_TOOL_POISONING_DECEPTION) critical

Mitigation: Remove references to sensitive data collection.

Data exfiltration patterns: INSTRUCTED_SENSITIVE_SERVICE_ACCESS high

Mitigation: Clearly document which sensitive services are accessed and why; use minimal required permissions

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:agentcloak:1.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T14:29:17.497Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "AgentCloak - Email Proxy that filters PII, 2FA, and password resets",
    "version": "1.0.0",
    "format": "agent_skill",
    "description": "\"Secure email proxy for AI agents. Search, read, and draft emails via MCP with server-side credential isolation, PII redaction, prompt injection detection, and content filtering. Unlike raw Gmail/IMAP skills, your agent never sees passwords or unfiltered content. Self-host or use the hosted version.\"",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "17fb2453b45486050aaa6803438d86203262d25b38edbaffe60bd89b0323fca0",
      "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": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "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": [
      "web"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 3,
      "D": 4,
      "A": 0,
      "C": 1
    },
    "flags": [
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_GIT_CLONE_AND_BUILD: Instructs agent to clone and potentially build from source"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION: Skill description is too vague or missing"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_SENSITIVE_DATA, MCP_TOOL_POISONING_DECEPTION"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "INSTRUCTED_SENSITIVE_SERVICE_ACCESS: Instructs agent to access sensitive services (email, calendar, contacts, drive)"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 4 security patterns (5 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H3: Shell/code execution or persistence detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "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": "Unauthorized tool use: INSTRUCTED_GIT_CLONE_AND_BUILD",
        "severity": "medium",
        "mitigation": "Use pre-built packages or vendored dependencies instead of cloning repos"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_SENSITIVE_DATA, MCP_TOOL_POISONING_DECEPTION)",
        "severity": "critical",
        "mitigation": "Remove references to sensitive data collection."
      },
      {
        "risk": "Data exfiltration patterns: INSTRUCTED_SENSITIVE_SERVICE_ACCESS",
        "severity": "high",
        "mitigation": "Clearly document which sensitive services are accessed and why; use minimal required permissions"
      }
    ],
    "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": "INSTRUCTED_GIT_CLONE_AND_BUILD [MEDIUM] SKILL.md:52: git clone https://github.com/ryanfren/AgentCloak.git",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "INSTRUCTED_SENSITIVE_SERVICE_ACCESS [HIGH] SKILL.md:3: description: \"Secure email proxy for AI agents. Search, read, and draft emails v",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_SENSITIVE_DATA [HIGH] SKILL.md:74: | `search_emails` | Search emails with Gmail-style queries | `query`, `max_resul",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_DECEPTION [CRITICAL] SKILL.md:139: | Hosted version | Your email credentials are stored server-side (encrypted). Em",
      "file_path": "SKILL.md"
    }
  ]
}