MakePost App Growth (via makepost.com)

Security checks across malware telemetry and agentic risk

Overview

MakePost appears purpose-aligned, but it gives the agent broad power to publish public content and manage app/business settings through a single API key.

Only install this if you trust MakePost and are comfortable giving the agent access to connected social and App Store-related accounts. Use a dedicated API key, connect only the accounts you need, require explicit confirmation before publishing, deleting, or changing pricing, and revoke the key if anything looks wrong.

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.

#
ASI02: Tool Misuse and Exploitation
High
What this means

A mistaken or over-eager agent action could publish content publicly or delete scheduled posts across connected social accounts.

Why it was flagged

The skill exposes high-impact public posting and deletion actions, including immediate publishing by default, with no visible confirmation or containment requirement in the provided artifact.

Skill content
"publish_content" — Create and publish content ... to one or more accounts ... "scheduled_at" ... Omit to publish immediately ... "is_draft" (bool, default false); "cancel_scheduled_post" ... The post is permanently deleted.
Recommendation

Use explicit confirmations for publishing, cancellation, and pricing changes; prefer draft-first workflows; and limit connected accounts or API scopes where MakePost supports it.

#
ASI03: Identity and Privilege Abuse
High
What this means

If the key is misused or the agent takes an unintended action, connected social channels and app-business settings could be affected.

Why it was flagged

The MakePost API key appears to delegate authority over multiple third-party social accounts plus App Store Connect/app-business functions, but the provided artifacts do not show least-privilege scoping or role limits.

Skill content
Setup: "Connect your social accounts" and "connect App Store Connect credentials"; Auth: "Authorization: Bearer <MAKEPOST_API_KEY>"; description: "control subscription pricing".
Recommendation

Use a dedicated, revocable API key; connect only necessary accounts; apply provider-side roles/scopes if available; and monitor or rotate the key regularly.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

A future or compromised helper package version could change how the MCP bridge behaves.

Why it was flagged

The MCP bridge is launched through `npx mcp-remote` without a pinned package version, so runtime behavior depends on the npm package resolution.

Skill content
"command": "npx", "args": ["mcp-remote", "https://makepost.com/api/mcp/", "--header", "Authorization: Bearer ${MAKEPOST_API_KEY}"]
Recommendation

Prefer a pinned `mcp-remote` version or a reviewed local installation, and keep the helper updated from a trusted source.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

MakePost receives the API-authorized requests and any data the agent sends through these tools.

Why it was flagged

Authenticated MCP traffic is sent to MakePost's remote MCP endpoint. This is expected for the service, but it is an important external data and credential boundary.

Skill content
"https://makepost.com/api/mcp/", "--header", "Authorization: Bearer ${MAKEPOST_API_KEY}"
Recommendation

Install only if you trust MakePost with the connected account actions and review MakePost's privacy and access controls before use.