Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Messages

A comprehensive AI agent skill for managing the full spectrum of incoming messages across email, chat, and other communication channels. Triages by urgency a...

MIT-0 · Free to use, modify, and redistribute. No attribution required.
0 · 163 · 0 current installs · 0 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
high confidence
!
Purpose & Capability
The skill claims cross-channel access (email, Slack, WhatsApp, iMessage, Teams, LinkedIn, Telegram, etc.), needs to read sent messages and full conversation history, and performs actions like unsubscribe and follow-ups — but the package declares no required environment variables, API keys, or config paths. Accessing those services legitimately requires credentials and explicit OAuth flows; the absence of any declared credential or integration points is disproportionate and incoherent with the stated purpose.
!
Instruction Scope
The SKILL.md explicitly instructs the agent to read your existing sent messages, check every channel for conversation history, draft replies in your voice, track threads, and perform unsubscribe/mute actions. Those instructions direct the agent to read and act on highly sensitive personal and business communications across multiple services; they do not specify how credentials are obtained, what endpoints are used, or any limits on data collection or external transmission.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which minimizes immediate disk-writing risk. However, the lack of an install mechanism contributes to the incoherence because there is no documented OAuth or connector flow for obtaining the broad access the instructions require.
!
Credentials
No environment variables, secrets, or primary credential are declared, yet the skill clearly needs many (email account credentials or OAuth tokens, chat API tokens, phone-linked/message-backend access). The requested scope implied by the instructions (read/write across many channels, access to sent-mail archive, contact and thread metadata) is large and sensitive; it is not justified or described in the metadata.
Persistence & Privilege
always: false (normal) and autonomous invocation is allowed (platform default). These settings are reasonable for the skill type; however, if you later grant broad credentials, autonomous invocation increases the potential blast radius (noted as a user consideration).
What to consider before installing
Do not install or grant access yet. Ask the publisher for specifics before proceeding: which channels are supported, exactly what credentials or OAuth scopes the skill requires, how tokens are obtained and stored, whether any message content or metadata is sent to external servers or third parties, and whether drafts or message data are retained. Prefer skills that use platform-managed OAuth flows with least-privilege scopes (read-only inbox vs full send/delete), provide an auditable privacy/security policy, and have a verifiable source repository or homepage. If you must try it, test with a dummy account and limit granted scopes; never provide permanent elevated credentials without clear, documented justification and review.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.0
Download zip
communicationvk97afrpq0preha3ng5mkg8f4r982grrjinboxvk97afrpq0preha3ng5mkg8f4r982grrjlatestvk97afrpq0preha3ng5mkg8f4r982grrjmessagesvk97afrpq0preha3ng5mkg8f4r982grrjrepliesvk97afrpq0preha3ng5mkg8f4r982grrjtriagevk97afrpq0preha3ng5mkg8f4r982grrj

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

SKILL.md

Messages

120 Messages a Day

That is the average number of messages a working professional receives across all channels daily. Email. Slack. WhatsApp. iMessage. LinkedIn. Teams. Telegram. Each platform optimized to surface everything with equal urgency, which means nothing has real urgency, which means the actually important things get buried.

The math on attention is brutal. If you spend an average of ninety seconds per message — reading, deciding, responding or deferring — 120 messages costs three hours of your day. Every day. That is roughly 700 hours per year. Seventeen and a half standard work weeks. Gone to message triage.

And that is assuming you are making good decisions in those ninety seconds. Most people are not. The context-switching cost of moving between a project, an urgent client message, a team chat notification, and a promotional email before returning to the project is a cognitive tax that compounds with every interruption.

Messages does not reduce the volume of what people send you. It radically reduces the cost of dealing with it.


The Daily Message Briefing

Once a day — or whenever you ask — the skill produces a complete picture of your incoming messages across all connected channels.

Everything is sorted into four categories based on genuine urgency and importance, not the sender's perception of those things.

Requires your response today. These are messages where delay has a real cost — a client waiting on a decision, a colleague blocked on your input, a time-sensitive opportunity. This list is kept deliberately short. If everything is urgent, nothing is.

Requires your response this week. Important but not time-critical. These get attention, just not right now.

Useful to know, no action needed. Information worth having. Status updates, FYI forwards, replies to threads you initiated. Summarized collectively so you can absorb the substance without reading each one.

Noise. Promotional content, automated notifications, newsletters from lists you forgot you joined, social platform alerts. Counted and batched. Never individually surfaced. Cleared efficiently with your confirmation.


Replies Written in Your Voice

For every message in the first category, the skill drafts a reply.

Voice matching is not a feature that works once and then gets forgotten. The skill reads your existing sent messages — the way you open conversations, the length you tend to write, the level of formality you use with different people, the phrases that are distinctively yours — and applies this understanding to every draft.

The result is a reply that sounds like you wrote it, because in the most meaningful sense, you did. The skill assembled the right words in the right order for this specific person and this specific situation. You review, adjust if needed, and approve.

Nothing is ever sent without your explicit sign-off on the exact text. Not a summary of what will be sent. The exact text, as it will appear to the recipient.


Thread Tracking

Sent a message that requires a reply? The skill tracks it automatically. Sets a follow-up window based on context — shorter for urgent matters, longer for things that can wait — and surfaces the thread if no reply arrives within that window.

When it does surface, it drafts the follow-up for you. Specific reference to the original message. Professional tone. No passive aggression. Just a clear, human nudge.

For important threads where you are waiting on multiple people, it tracks each one separately and follows up on the slowest responders first.


Noise Reduction Over Time

The skill monitors your response patterns. Senders whose messages you consistently ignore, archive without reading, or mark as low priority get flagged for review. It presents a periodic list of sources generating noise without value and handles the unsubscribe or mute action with your confirmation.

This is not a one-time inbox cleanup. It is an ongoing process that makes your communication environment progressively cleaner over months of use.


Cross-Channel Intelligence

The same person communicates with you across multiple channels. A client emails formally but also sends casual WhatsApp messages. A colleague uses Slack for quick questions and email for anything that needs a record. A business contact connects on LinkedIn and later moves to direct email.

The skill maintains a unified view of each relationship across every channel. When you ask "has Michael gotten back to me about the proposal," it checks everywhere — not just the last place you remember the conversation happening. When you are drafting a reply, it surfaces the full conversation history regardless of where each message was sent.


Weekly Communication Review

Every week the skill produces a short review of your communication patterns: average response time, channels generating the most noise, threads that have gone quiet and may need attention, and relationships where communication has dropped off more than usual.

Not to judge how you are managing your messages. To give you visibility into patterns you cannot see when you are inside them.


The Underlying Principle

You became good at your work by developing judgment, expertise, and relationships over years. None of those things require you to personally read and process every notification that arrives in your direction. Triage is a mechanical task. Drafting routine replies is a mechanical task. Tracking who owes you a response is a mechanical task.

Mechanical tasks belong to systems. Your attention belongs to the work that actually requires you.

Files

1 total
Select a file
Select a file to preview.

Comments

Loading comments…