LinkedIn Automation by Zich (BradAI's OpenClaw)

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: linkedin-automation Version: 1.0.0 The skill bundle is designed for LinkedIn automation, requiring the declared 'browser' tool. All scripts (`analytics.sh`, `engage.sh`, `ideas.sh`, `post.sh`, `schedule.sh`) output clear, explicit instructions for the AI agent to perform browser actions or schedule tasks using OpenClaw's native cron tool, directly aligning with the stated purpose. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts to subvert the agent for harmful activities. The instructions are consistently within the expected scope of LinkedIn automation.

Findings (0)

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 carelessly, the agent could publish content or interact with others in ways that affect the user's professional reputation.

Why it was flagged

The skill is explicitly designed to perform public LinkedIn actions through browser automation, including posting and commenting.

Skill content
Use for posting content, scheduling posts, analyzing engagement metrics, generating content ideas, commenting on posts, and building LinkedIn presence.
Recommendation

Review post text, images, comments, and engagement limits before approving browser actions, especially when actions will be visible publicly.

What this means

The agent can use the logged-in LinkedIn account to view account-specific analytics and perform account actions.

Why it was flagged

The skill relies on an active LinkedIn browser session, which lets the agent act using the user's authenticated account.

Skill content
LinkedIn logged in via browser (use profile with LinkedIn session)
Recommendation

Use only with the intended LinkedIn profile, and do not let the agent proceed if you are logged into the wrong account or a shared browser profile.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

A scheduled job may publish later, even after the original session, if the user forgets about it or schedules the wrong content.

Why it was flagged

The skill documents creating persistent scheduled jobs that can trigger future LinkedIn posting.

Skill content
For scheduled posts, use OpenClaw cron: cron add --schedule "0 9 * * 1-5" --payload "Post my LinkedIn content: [content]"
Recommendation

Keep a list of scheduled LinkedIn jobs, verify their content and timing, and cancel any jobs you no longer want before they run.