This report is not translated for the requested language. The canonical English report is shown instead.

Versioned security assessment

Report ID: SA-62E2A730

7/5/2026, 7:53:21 PM

twitter-automation security assessment v3

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
twitter-automation
Version
v3
Maintainer
qu-skills
Source
github.com/qu-skills/skills/tree/main/tools/social/twitter-automation/
Coverage
1 Files scanned · 158 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

1 confirmed security finding requires attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Most backtick findings are Markdown formatting, but several examples intentionally run belt or npx commands. No prompt injection was found, but the skill has real side effects through X account automation.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 158 Lines analyzed

17 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 7 evidence locations

Filesystem access

May read or write local files.

Not recorded by this audit

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 37 evidence locations

Capability review items (16)
Medium
SKILL.md:7
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
The inline text tells users to run `npx skills add belt-sh/cli`. That can fetch and install external skill code if followed.
Medium
SKILL.md:19-24
Ruby/shell backtick execution
```bash
This block includes `belt login` and a `belt app run` command. It can post through an authenticated X account.
Medium
SKILL.md:45-47
Ruby/shell backtick execution
```bash
This block runs `belt app run x/post-tweet`. It can publish content through an authenticated X account.
Medium
SKILL.md:51-61
Ruby/shell backtick execution
```bash
This block runs `belt app sample` and `belt app run x/post-create`. It can create a media post through the external service.
Medium
SKILL.md:65-67
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/post-like`. It can change account engagement state on X.
Medium
SKILL.md:71-73
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/post-retweet`. It can amplify a post from the authenticated X account.
Medium
SKILL.md:77-82
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/dm-send`. It can send direct messages from the authenticated account.
Medium
SKILL.md:86-88
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/user-follow`. It can follow a user from the authenticated account.
Medium
SKILL.md:92-94
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/user-get`. It performs an external account lookup through the CLI.
Medium
SKILL.md:98-100
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/post-get`. It performs an external post lookup through the CLI.
Medium
SKILL.md:104-106
Ruby/shell backtick execution
```bash
This block invokes `belt app run x/post-delete`. It can delete a post from the authenticated account.
Medium
SKILL.md:110-119
Ruby/shell backtick execution
```bash
This workflow runs media generation and Twitter posting commands through `belt`. It writes local output and posts external media.
Medium
SKILL.md:123-132
Ruby/shell backtick execution
```bash
This workflow runs video generation and Twitter posting commands through `belt`. It writes local output and posts external media.
Medium
SKILL.md:136-148
Ruby/shell backtick execution
```bash
This block lists `npx skills add` commands for related skills. Running them can install additional unreviewed code or instructions.
Low
SKILL.md:13
Hardcoded URL
![Twitter/X Automation](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgad3pxs
The Markdown image points to an external `cloud.inference.sh` asset. Rendering the skill may contact that host.
Low
SKILL.md:17
Hardcoded URL
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
The install instructions link uses a raw GitHub URL on the main branch. Following it fetches remote instructions.

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:3SKILL.md:37-38SKILL.md:75-87
Automated Social Media Action Abuse
The skill supports posting, liking, retweeting, sending direct messages, and following users. These actions can enable spam or unwanted engagement without controls.
The capability list and examples directly include DM and follow operations. The file does not include approval, rate-limit, or recipient validation guidance.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    External CLI commands can mutate X account state.
    Require explicit approval before posting, deleting, liking, retweeting, following, or sending a direct message.
  2. FIX-002
    Medium
    Transitive skill installation commands use npx and unpinned references.
    Pin trusted versions and keep dependency installation outside automated social workflows.
  3. FIX-003
    Medium
    Automated engagement can be used for spam.
    Add guidance for rate limits, recipient validation, and platform policy compliance.
  4. FIX-004
    Low
    The Markdown image loads from an external host.
    Bundle a reviewed asset or disclose that viewing the skill may load remote media.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable