Line Client

SuspiciousAudited by ClawScan on May 10, 2026.

Overview

This is a broad LINE account-control skill that can read and change messages, contacts, and groups while relying on stored login tokens and unreviewed external code.

Only install or use this if you are comfortable giving the skill broad control of your LINE account. Confirm the external code source, protect and clean up `~/.line-client` tokens, and require manual approval before any message, deletion, contact, or group-management action.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If invoked incorrectly, the agent could send unwanted LINE messages, remove chats, block contacts, or change group membership.

Why it was flagged

These documented methods can send or remove messages and alter contacts/groups, but the artifact does not define confirmation rules, allowed targets, or containment for those high-impact actions.

Skill content
`send_message(to, text, ...)`, `unsend_message(message_id)`, `send_chat_removed(...)`, `block_contact(mid)`, `create_chat(...)`, `invite_into_chat(...)`, `delete_other_from_chat(...)`, `leave_chat(chat_id)`
Recommendation

Require explicit user confirmation for sending, deleting, blocking, inviting, kicking, or leaving actions, and scope use to user-specified chats or contacts.

What this means

Anyone or any agent process with access to those tokens may be able to act as the user's LINE account for the token lifetime.

Why it was flagged

The skill uses persistent LINE auth and refresh tokens that grant account access; registry metadata declares no primary credential or required config path, so the credential boundary is under-specified.

Skill content
`Token storage: ~/.line-client/tokens.json` ... `client = LineChromeClient(auth_token=tokens["auth_token"])` ... `result.auth_token, result.mid, result.refresh_token`
Recommendation

Declare the credential requirement, document token permissions and retention, protect the token file, and provide clear logout/cleanup guidance.

What this means

Users would need to trust external or local code that is not included in the reviewed package before granting LINE account access.

Why it was flagged

The provided artifact set contains only SKILL.md and no install spec or code files, so the referenced authentication, signer, and client code needed for high-impact account operations is not reviewable here.

Skill content
`Repo: /data/workspace/line-client` ... `github.com/2manslkh/line-api`; `Main client: src/chrome_client.py`; `QR login: src/auth/qr_login.py`; `HMAC signer: src/hmac/signer.js`; `WASM files: lstm.wasm + lstmSandbox.js`
Recommendation

Package the required code with the skill, pin and verify external sources, and include an install specification so the authentication and messaging implementation can be reviewed.

What this means

LINE message and account requests may be sent to the documented gateway as part of normal operation.

Why it was flagged

The skill is expected to communicate with the LINE Chrome extension gateway, which means message and account operations leave the local environment for the provider API.

Skill content
`Provides HMAC-signed API access through the Chrome extension gateway (line-chrome-gw.line-apps.com)`
Recommendation

Use only the expected LINE account, verify the destination gateway, and avoid sending sensitive chats or files unless necessary.