# Send AgentCloak - Email Proxy that filters PII, 2FA, and password resets to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "agentcloak-email-proxy", "name": "AgentCloak - Email Proxy that filters PII, 2FA, and password resets", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ryanfren/agentcloak-email-proxy", "canonicalUrl": "https://clawhub.ai/ryanfren/agentcloak-email-proxy", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/agentcloak-email-proxy", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentcloak-email-proxy", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "agentcloak-email-proxy", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T13:53:05.044Z", "expiresAt": "2026-05-06T13:53:05.044Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentcloak-email-proxy", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentcloak-email-proxy", "contentDisposition": "attachment; filename=\"agentcloak-email-proxy-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "agentcloak-email-proxy" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/agentcloak-email-proxy" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/agentcloak-email-proxy", "downloadUrl": "https://openagent3.xyz/downloads/agentcloak-email-proxy", "agentUrl": "https://openagent3.xyz/skills/agentcloak-email-proxy/agent", "manifestUrl": "https://openagent3.xyz/skills/agentcloak-email-proxy/agent.json", "briefUrl": "https://openagent3.xyz/skills/agentcloak-email-proxy/agent.md" } } ``` ## Documentation ### AgentCloak Secure email proxy for AI agents. AgentCloak sits between your agent and your email, so the agent gets useful email access without seeing credentials, sensitive financial data, PII, or prompt injection attacks. Every other email skill on ClawHub gives your agent raw, unfiltered access to your inbox. AgentCloak is the only one with a built-in security pipeline. ### What makes this different Credential isolation — your email password/OAuth tokens stay server-side; the agent only has an API key 4-stage content filter — blocklist, HTML sanitizer, PII redaction, prompt injection detection Read + draft only — agents can search, read, list, and draft emails but cannot send, delete, or modify anything Draft safety — drafts are never sent automatically; you review them first Self-host or hosted — run your own instance or use the hosted version ### Option A: Hosted version (quickest) Sign up at https://agentcloak.up.railway.app Connect your email (IMAP works with any provider, Gmail OAuth available by invite) Create an API key in the dashboard Configure: export AGENTCLOAK_API_KEY=ac_your_key_here mcporter config add agentcloak \\ --baseUrl "https://agentcloak.up.railway.app/mcp" \\ --header "Authorization: Bearer $AGENTCLOAK_API_KEY" ### Option B: Self-hosted Clone and run: git clone https://github.com/ryanfren/AgentCloak.git cd agentcloak pnpm install && pnpm build && pnpm dev Open http://localhost:3000, create an account, connect email, create API key Configure: export AGENTCLOAK_URL=http://localhost:3000 export AGENTCLOAK_API_KEY=ac_your_key_here mcporter config add agentcloak \\ --baseUrl "${AGENTCLOAK_URL}/mcp" \\ --header "Authorization: Bearer $AGENTCLOAK_API_KEY" Requirements for self-hosting: Node.js 20+, pnpm 10+ ### Available tools ToolDescriptionKey parameterssearch_emailsSearch emails with Gmail-style queriesquery, max_results (1-200), page_tokenread_emailRead full email content by IDmessage_idlist_threadsList conversation threadsquery, max_results, page_tokenget_threadRead all messages in a threadthread_idcreate_draftCreate a draft (not sent)to, subject, body, in_reply_to_thread_idlist_draftsList existing draftsmax_resultslist_labelsList all labels with unread counts(none)get_provider_infoGet provider type and capabilities(none) ### Usage examples # Search for unread emails mcporter call agentcloak.search_emails query:"is:unread" max_results:10 # Read a specific email mcporter call agentcloak.read_email message_id:"abc123" # Get a full conversation thread mcporter call agentcloak.get_thread thread_id:"thread456" # Draft a reply (not sent until you review it) mcporter call agentcloak.create_draft subject:"Re: Meeting" body:"Sounds good, see you Thursday." in_reply_to_thread_id:"thread456" # List labels and unread counts mcporter call agentcloak.list_labels ### Security pipeline Every email passes through a 4-stage filter before the agent sees it. Each stage is independently configurable from the dashboard. ### Stage 1: Blocklist Blocks emails from sensitive senders outright. Three toggleable categories: Financial — 40+ domains (Chase, PayPal, Venmo, Coinbase, etc.) Security senders — patterns like security@, fraud@, alerts@, .gov addresses Security subjects — password resets, 2FA codes, verification links, login alerts Plus custom blocklists: add your own domains, sender patterns, or subject patterns. ### Stage 2: HTML sanitizer Converts HTML email to plaintext and strips dangerous Unicode (zero-width characters, bidirectional overrides, tag characters, variation selectors) that could be used to hide prompt injection. ### Stage 3: PII redaction Redacts sensitive patterns with placeholders: SSNs, credit card numbers, bank account/routing numbers API keys (sk_, pk_, AWS keys), bearer tokens, PEM private keys Optionally: email addresses, large dollar amounts ### Stage 4: Prompt injection detection Scans for 19 known injection patterns (instruction overrides, role reassignments, system tag injections, data exfiltration attempts). Flags detected content with a [AGENTCLOAK WARNING] prefix so the agent knows the email may be adversarial. Does not block — lets the agent make an informed decision. ### Security and privacy What data leaves your machine: ScenarioData flowSelf-hostedNothing leaves your machine. All processing is local.Hosted versionYour email credentials are stored server-side (encrypted). Email content passes through the hosted server's filter pipeline. No data is shared with third parties. API keys are hashed (SHA-256) before storage — the server cannot recover your key after creation Email credentials are stored server-side; the agent never sees them All filtering happens server-side before content reaches the agent The agent can only read and draft — it cannot send, delete, or modify emails Source code is open: https://github.com/ryanfren/AgentCloak Trust statement: By using the hosted version, you trust the AgentCloak server with access to your email account credentials and content. If this is not acceptable, self-host your own instance for full control. ### Email providers AgentCloak supports three connection methods: IMAP — works with any email provider (Gmail, Outlook, ProtonMail Bridge, Fastmail, etc.) Gmail OAuth — direct API access (currently invite-only during beta) Gmail Apps Script — manual setup via script.google.com, no Google Cloud project needed ### Limitations Read and draft only — no send, delete, or modify Gmail search syntax only (even for IMAP connections, queries are translated) Attachment content is not accessible (metadata can optionally be shown) Gmail OAuth is invite-only during beta; IMAP and Apps Script are open to all Hosted version is in beta ### Links Homepage: https://agentcloak.up.railway.app Source: https://github.com/ryanfren/AgentCloak License: BSL 1.1 ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ryanfren - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-29T13:53:05.044Z - Expires at: 2026-05-06T13:53:05.044Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/agentcloak-email-proxy) - [Send to Agent page](https://openagent3.xyz/skills/agentcloak-email-proxy/agent) - [JSON manifest](https://openagent3.xyz/skills/agentcloak-email-proxy/agent.json) - [Markdown brief](https://openagent3.xyz/skills/agentcloak-email-proxy/agent.md) - [Download page](https://openagent3.xyz/downloads/agentcloak-email-proxy)