X Engagement

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent X/Twitter engagement assistant, but users should notice that it controls a logged-in browser, can perform public account actions after confirmation, and stores local engagement memory.

Before installing or using this skill, make sure you are comfortable letting it operate a logged-in X/Twitter browser session. Keep the documented confirmation flow enabled, verify the Browser Relay CLI before running `npx`, and periodically inspect or clean the local memory files that store your activity and personal facts.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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 used, the agent may like, follow, or comment from the user's X account, which can affect the user's public profile and reputation.

Why it was flagged

The skill can drive browser actions that mutate an X/Twitter account, but the documented flow requires preview and user confirmation before these write actions.

Skill content
点赞、关注、评论都先生成建议,再由用户确认是否执行
Recommendation

Only approve actions after reviewing the exact target tweet/account and final text; do not enable any workflow that bypasses the confirmation steps.

What this means

Actions are performed as the currently logged-in X user, so using the wrong browser profile or account could cause unintended public activity.

Why it was flagged

The skill relies on the user's already-authenticated browser session rather than a separate API token, giving it delegated access to the logged-in X account through browser automation.

Skill content
Chrome/Chromium 已登录目标 X 账号
Recommendation

Use a dedicated browser profile or tab for the intended X account and confirm the logged-in identity before allowing any write action.

What this means

Running an unverified or changed external package could expose the browser automation channel to code outside this reviewed skill.

Why it was flagged

The documented setup runs an external CLI through `npx` without a pinned version in the skill artifacts. This is central to the browser-control purpose, but it is still external code execution.

Skill content
npx browser-relay-cli version
npx browser-relay-cli extension-path
npx browser-relay-cli relay-start
Recommendation

Verify the Browser Relay project and npm package, consider pinning a known version, and review the external tool before running it with a logged-in browser.

What this means

Personal statements and engagement history may persist locally and influence future public comments or recommendations.

Why it was flagged

The memory design stores user facts, preferences, comment history, personas, and daily logs, with some data retained permanently and reused in future comment generation.

Skill content
用户事实 | 永久 | 一直保留
Recommendation

Review the memory directory periodically, delete facts you do not want retained, and be cautious about letting untrusted social content become long-term playbook guidance.