Instagram Content Studio

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill mostly matches its Instagram-management purpose, but it uses powerful account tokens and refresh outputs can expose access tokens in agent logs, so it should be reviewed before use.

Use this only with a dedicated Meta app and minimum permissions. Review every publish/comment action before approving it, avoid sharing refresh-command output or logs, and only upload local files you are comfortable briefly exposing through a temporary tunnel.

Findings (5)

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 an access token is exposed in logs or chat history, someone with access to it may be able to manage the connected Instagram/Facebook account until the token is revoked or expires.

Why it was flagged

The refresh helper returns the full refreshed access token, and the refresh scripts serialize their result to stdout. This can place a live credential in agent transcripts or logs.

Skill content
return { access_token: newToken, expires_in: data.expires_in, expires_in_days: expiresInDays };
Recommendation

Avoid running refresh commands unless necessary, do not share logs containing refresh output, and consider changing the scripts to omit or redact access_token from stdout.

What this means

A mistaken approval could publish unwanted media or comments on the connected Instagram account.

Why it was flagged

The skill can publish posts and write comments/replies, which are public account mutations; the instructions add a confirmation step before those actions.

Skill content
When publishing images or videos, always confirm the caption with the user before executing. ... When writing comments/replies, confirm the content with the user before executing.
Recommendation

Review the exact media path/URL, caption/comment text, and target post/comment ID before approving any publish or comment command.

What this means

Using local media posting will run cloudflared on the user's machine.

Why it was flagged

The code starts an external cloudflared process for local uploads. The command is fixed and matches the disclosed upload mechanism.

Skill content
tunnelProcess = spawn("cloudflared", [
      "tunnel",
      "--url",
      `http://localhost:${port}`,
    ]);
Recommendation

Install cloudflared only from a trusted source and use local uploads only when you understand that a temporary tunnel will be created.

What this means

Any local file selected for upload may be briefly reachable through the tunnel during posting.

Why it was flagged

Selected local files are temporarily exposed through a Cloudflare tunnel so Instagram can download them. This is disclosed and purpose-aligned, but it affects local file privacy.

Skill content
Local image/video posting starts a temporary cloudflared Quick Tunnel ... Only provide file paths you are comfortable briefly exposing to the internet.
Recommendation

Only provide file paths for media you are comfortable temporarily exposing, and avoid private or unrelated files.

What this means

Installing external binaries or npm dependencies can add supply-chain risk if the source is not trusted.

Why it was flagged

The documented setup includes a user-directed download and privileged installation of the latest cloudflared package. This is not automatic, but it requires trusting the download source.

Skill content
curl -L -o cloudflared.deb https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-$(dpkg --print-architecture).deb
sudo dpkg -i cloudflared.deb
Recommendation

Verify the skill source and install cloudflared/dependencies through trusted package managers or pinned, verified releases where possible.