Social Media Engine

SuspiciousAudited by ClawScan on May 10, 2026.

Overview

This is a real social-media automation skill, but it can queue or publish posts with your social accounts and its “draft by default” safety promise is contradicted by the included script.

Install only if you are comfortable giving the agent access to Buffer or Postiz credentials for your social accounts. Before using it, confirm that commands save drafts unless you explicitly want posts queued, scheduled, or published, and review the exact channel, content, and time for every posting 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 the agent runs the scheduler with valid credentials, content may be queued, scheduled, or posted on connected social channels, affecting the user's public accounts.

Why it was flagged

The script defaults Buffer posts to the queue and Postiz posts to immediate posting unless --draft is supplied, so the posting tool can create public or scheduled account actions rather than drafts by default.

Skill content
let mode = 'addToQueue'; ... ...(opts.draft ? { saveToDraft: true } : {}); ... let type = 'now'; if (opts.draft) type = 'draft'; else if (opts.schedule) type = 'schedule';
Recommendation

Use explicit --draft behavior by default, require a separate explicit publish/queue confirmation, and verify the exact channel and time before allowing the agent to run posting commands.

What this means

A user may trust that generated posts cannot publish without later human review, when the script may instead queue or publish depending on platform and arguments.

Why it was flagged

This user-facing safety assurance conflicts with the included scheduler defaults that only save drafts when --draft is provided.

Skill content
All posts are created as DRAFTS by default — human approval required before publishing.
Recommendation

Correct the documentation and code so they match: either make drafts the enforced default or clearly warn when a command will queue, schedule, or publish content.

What this means

Anyone or any agent run with these environment variables can potentially list channels and create posts through Buffer or Postiz.

Why it was flagged

The skill needs delegated API credentials for social posting services. That is purpose-aligned, but those credentials can act on connected social accounts.

Skill content
requiredEnv: - BUFFER_API_KEY ... - POSTIZ_API_KEY ... permissions: - network: Calls Buffer GraphQL API or Postiz API to schedule and retrieve posts
Recommendation

Use least-privilege or separate posting keys where possible, keep credentials in a scoped project environment, and rotate/revoke them if the skill is removed or no longer trusted.

What this means

Following the optional setup guide without review could run code outside the reviewed skill artifacts.

Why it was flagged

The optional self-hosted Postiz setup guide tells users to execute a remote installer script. This is not automatic skill execution, but it is a supply-chain-sensitive setup step.

Skill content
curl -fsSL https://get.docker.com | sh
Recommendation

Install Docker/Postiz using trusted official instructions, inspect remote scripts before running them, and pin or verify versions where practical.