Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Agenticmail

skill · InternLM/WildClawBenchMIT licenceAudited 15 Oct 2026 · source a79d9cd3663a

★ 533pushed 27 days ago
!CAUTIONGrade B · 89/100 · 6 findings · a79d9cd
533repo stars · whole InternLM/WildClawBench

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit a79d9cd3663a and observed filesystem and network access and no hard-coded secrets. The audit raised 6 findings, 0 critical or high. What it does: 🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Agenticmail (InternLM/WildClawBench)”. Retrieved 15 Oct 2026. https://modelsatlas.com/skills/internlm/agenticmail

Trust audit

Audit 0.4.1 · source read 15 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high2 medium4 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemDeclared1 observation
  • NetworkDeclared4 observations
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN6
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (6)

MEDIUMNetwork egressnet.raw_ip · SKILL.md:217
F-04 Network egressCWE-200 · CWE-319Layer L1
"apiUrl": "http://127.0.0.1:3100",
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · scripts/health-check.sh:12
F-04 Network egressCWE-200 · CWE-319Layer L1
if curl -sf http://127.0.0.1:3100/api/agenticmail/health > /dev/null 2>&1; then
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/setup.sh:21
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · references/api-reference.md:3
F-04 Network egressCWE-200 · CWE-319Layer L1
Base URL: `http://127.0.0.1:3100/api/agenticmail`
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · references/configuration.md:33
F-04 Network egressCWE-200 · CWE-319Layer L1
"apiUrl": "http://127.0.0.1:3100",
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · references/configuration.md:57
F-04 Network egressCWE-200 · CWE-319Layer L1
"AGENTICMAIL_API_URL": "http://127.0.0.1:3100",
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha a79d9cd3663a · 15 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherInternLM GitHub organizationOwner of the repository this skill is read from
  • Source folderInternLM/WildClawBench/skills/3/agenticmailThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicta79d9cd3663aA new audit runs when the source changes
  • Repository statusNot archivedLast push 27 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: 🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.

---
name: agenticmail
description: 🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.
homepage: https://github.com/agenticmail/agenticmail
metadata: { "openclaw": { "emoji": "🎀", "primaryEnv": "AGENTICMAIL_API_KEY", "requires": { "bins": ["docker"], "config": ["plugins.entries.agenticmail.config.apiKey"] } } }
---

# 🎀 AgenticMail

Email, SMS, database storage & multi-agent coordination for AI agents. Gives your agent a real mailbox, phone number, and persistent storage — 63 tools covering email, SMS, database management, and inter-agent task delegation. Includes outbound security guard, spam filtering, human-in-the-loop approval, and automatic follow-up scheduling.

## Quick Setup

```bash
agenticmail openclaw
```

That's it. The command sets up the mail server, creates an agent account, configures the plugin, and restarts the gateway.

## Tools

### Core Email (8 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_send` | Send an email with automatic PII/credential scanning and outbound security guard |
| `agenticmail_reply` | Reply to a message (outbound guard applied) |
| `agenticmail_forward` | Forward a message (outbound guard applied) |
| `agenticmail_inbox` | List recent emails in the inbox with pagination |
| `agenticmail_read` | Read a specific email by UID with security metadata (spam score, sanitization) |
| `agenticmail_search` | Search emails by from/subject/text/date/seen, optionally search relay account |
| `agenticmail_delete` | Delete an email by UID |
| `agenticmail_import_relay` | Import an email from connected Gmail/Outlook for thread continuation |

### Batch Operations (5 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_batch_read` | Read multiple emails at once by UIDs (token-efficient) |
| `agenticmail_batch_delete` | Delete multiple messages by UIDs |
| `agenticmail_batch_mark_read` | Mark multiple emails as read |
| `agenticmail_batch_mark_unread` | Mark multiple emails as unread |
| `agenticmail_batch_move` | Move multiple messages to another folder |

### Efficiency (2 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_digest` | Get a compact inbox digest with previews (efficient overview) |
| `agenticmail_template_send` | Send email using a saved template with variable substitution |

### Folders & Message Management (6 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_folders` | List all mail folders |
| `agenticmail_list_folder` | List messages in a specific folder (Sent, Drafts, Trash, etc.) |
| `agenticmail_create_folder` | Create a new mail folder |
| `agenticmail_move` | Move an email to another folder |
| `agenticmail_mark_unread` | Mark a message as unread |
| `agenticmail_mark_read` | Mark a message as read |

### Organization (7 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_contacts` | Manage contacts (list, add, delete) |
| `agenticmail_tags` | Manage tags/labels (list, create, delete, tag/untag messages) |
| `agenticmail_drafts` | Manage email drafts (list, create, update, delete, send) |
| `agenticmail_signatures` | Manage email signatures (list, create, delete) |
| `agenticmail_templates` | Manage email templates (list, create, delete) |
| `agenticmail_schedule` | Manage scheduled emails (create, list, cancel) |
| `agenticmail_rules` | Manage server-side email rules for auto-processing |

### Security & Moderation (3 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_spam` | Manage spam (list spam folder, report, mark not-spam, get spam score) |
| `agenticmail_pending_emails` | Check status of emails blocked by outbound security guard |
| `agenticmail_cleanup` | List or remove inactive non-persistent agent accounts |

### Inter-Agent Communication (3 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_message_agent` | Send a message to another AI agent by name (rate-limited) |
| `agenticmail_check_messages` | Check for new unread messages from other agents |
| `agenticmail_wait_for_email` | Wait for a new email using push notifications (SSE) |

### Agent Task Queue (5 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_call_agent` | Call another agent (sync or async). Preferred method for all delegation. |
| `agenticmail_check_tasks` | Check pending tasks (incoming or outgoing) |
| `agenticmail_claim_task` | Claim a pending task assigned to you |
| `agenticmail_submit_result` | Submit result for a claimed task |
| `agenticmail_complete_task` | Claim + submit in one call (for light-mode tasks) |

### Account Management (6 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_whoami` | Get current agent info (name, email, role, metadata) |
| `agenticmail_update_metadata` | Update agent metadata |
| `agenticmail_list_agents` | List all AI agents with emails and roles |
| `agenticmail_create_account` | Create a new agent email account (requires master key) |
| `agenticmail_delete_agent` | Delete an agent (archives emails, generates deletion report) |
| `agenticmail_deletion_reports` | List or view past agent deletion reports |

### Gateway & Admin (9 tools)
| Tool | Description |
|------|-------------|
| `agenticmail_status` | Check AgenticMail server health |
| `agenticmail_setup_guide` | Compare setup modes (Relay/Beginner vs Domain/Advanced) with requirements, pros/cons |
| `agenticmail_setup_relay` | Configure Gmail/Outlook relay for real internet email (Beginner) |
| `agenticmail_setup_domain` | Set up a custom domain via Cloudflare with optional Gmail SMTP relay (Advanced) |
| `agenticmail_setup_gmail_alias` | Get instructions to add agent email as Gmail "Send mail as" alias (for domain mode) |
| `agenticmail_setup_payment` | Get instructions to add payment method to Cloudflare (self-service link or browser automation) |
| `agenticmail_purchase_domain` | Search domain availability (purchase must be done manually on Cloudflare or other registrar) |
|

Excerpt, first 6,003 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit a79d9cd

Download folder ↗
git clone https://github.com/InternLM/WildClawBench
git -C WildClawBench checkout a79d9cd3663a

The author documents no install command, so this uses the repository directly. Our verdict covers commit a79d9cd3663a only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
WindsurfMentioned in its text, not testedSkills for Windsurf · About Windsurf
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source a79d9cd3663a

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/internlm/agenticmail/badge.svg)](https://modelsatlas.com/skills/internlm/agenticmail/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

03 Task1✓SAFE

InternLM/WildClawBench

Coordinates meeting scheduling via Gmail and Calendar APIs. Use when: scheduling a meeting, checking participant availability, sending coordination emails, creating calendar events, or notifying organizers of confirmed…

★ 533Grade B
03 Task2✓SAFE

InternLM/WildClawBench

Extracts action items and pending tasks from Slack messages. Use when: reviewing unread messages for todos, finding deadlines or requests directed at the user, or producing a task summary from recent Slack activity.

★ 533Grade B
03 Task3✓SAFE

InternLM/WildClawBench

Analyzes Slack messages to assess deal or project feasibility. Use when: synthesizing fragmented stakeholder input on a deal, identifying conflicting requirements or risks, or producing a feasibility report for…

★ 533Grade B
03 Task4✓SAFE

InternLM/WildClawBench

Reads recent Slack messages to compile an accurate project status report and saves it as a draft for review before sending to a client. Use when: preparing a client-facing update, reconciling conflicting or revised…

★ 533Grade B
03 Task5✓SAFE

InternLM/WildClawBench

Triages a support inbox, prioritizes urgent issues, routes each to the right internal team member, and drafts any customer-facing replies for review. Use when: catching up on a backlog of support messages, producing an…

★ 533Grade B
03 Task6✓SAFE

InternLM/WildClawBench

整合多部门 Slack 消息,交叉核对数据,识别依赖关系与风险,为高管起草董事会级别的执行摘要草稿。适用场景:跨部门项目状态汇总、董事会会议准备、需要数据对账和风险识别的高管报告。

★ 533Grade B

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/internlm/agenticmail/badge.svg)](https://modelsatlas.com/skills/internlm/agenticmail/)

Questions about Agenticmail

What does the Agenticmail skill do?
An in-the-wild benchmark for AI agents in the production harness.
Is Agenticmail safe to install?
With care. The audit graded it B (89/100) and found 6 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Agenticmail access on my machine?
The audit observed that it reaches the network and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does Agenticmail work with?
Its documentation mentions cursor, openclaw and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (a79d9cd3663a), read on 2026-10-15. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.