Skills twitter-automation
📦
twitter-automation
Content revision r2 Medium Risk ⚙️ External commands🌐 Network access
Automate Twitter and X Account Actions
Managing routine X actions across separate tools takes time and creates inconsistent workflows. This skill provides focused CLI commands for publishing, engagement, messaging, and retrieval.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "twitter-automation" from https://skillstore.io/skills/infsh-skills-twitter-automation.md and its manifest at https://skillstore.io/api/skills/infsh-skills-twitter-automation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "twitter-automation". Draft an X post announcing version 2.1 to existing users.
Expected outcome:
Version 2.1 is available with faster search and clearer export controls. Review the release notes and share your feedback.
Using "twitter-automation". Check the profile for OpenAI before preparing a response.
Expected outcome:
- Profile lookup prepared for OpenAI.
- No follow, message, like, or retweet action was performed.
- Review the retrieved profile details before approving another action.
Using "twitter-automation". Prepare a product image post and ask before publishing.
Expected outcome:
- Post text and media reference are prepared.
- The target account and final content require review.
- Publishing is waiting for explicit confirmation.
Security Audit
Medium Riskv5 • 8/6/2026 Open versioned report
The skill intentionally invokes inference.sh commands that can publish, delete, message, follow, and engage through an external X account. Most static alerts are Markdown syntax, but unpinned skill installation, a remote image, and automation abuse potential remain material concerns.
1
Files scanned
158
Lines analyzed
16
Review items
0
False positives ignored
Confirmed security concerns (2)
Medium
Unpinned Remote Skill Installation
The skill instructs users to install remote skills through npx without immutable versions or commits, allowing upstream changes to alter installed instructions.
The commands visibly reference package and repository names without version or commit pins. This is direct evidence of a mutable dependency boundary.
Medium
Social Platform Abuse Potential
The stated engagement-bot and audience-growth use cases combine with direct-message and follow commands, enabling unsolicited outreach or coordinated engagement.
The metadata explicitly promotes engagement bots and audience growth, while the examples provide direct-message and follow operations without consent or rate-limit controls.
Capability review items (16)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Medium
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
Line 7 instructs users to run an unpinned npx command that downloads another skill. This crosses a supply-chain boundary even though Markdown backticks do not execute it automatically.
Medium
Ruby/shell backtick execution
```bash
The Bash block runs belt login and posts a tweet through an external account. These are intended external commands with authentication and public side effects.
Medium
Ruby/shell backtick execution
```bash
The fenced example invokes belt to publish a tweet. It is a legitimate command, but it creates an external public side effect.
Medium
Ruby/shell backtick execution
```bash
This Bash block invokes belt, writes input.json, and publishes media through X. The commands have local filesystem and external account side effects.
Medium
Ruby/shell backtick execution
```bash
The Bash example runs belt to like a specified tweet. This intentionally changes engagement state on an external account.
Medium
Ruby/shell backtick execution
```bash
The Bash example invokes belt to retweet a specified post. This is an intended external command with a public account side effect.
Medium
Ruby/shell backtick execution
```bash
The Bash block invokes belt to send a direct message to a specified recipient. This transmits user-provided content to an external party.
Medium
Ruby/shell backtick execution
```bash
The Bash example invokes belt to follow a named user. This changes the authenticated account through an external service.
Medium
Ruby/shell backtick execution
```bash
The Bash example invokes belt to retrieve a user profile from X. It intentionally runs an external command and transmits a username.
Medium
Ruby/shell backtick execution
```bash
The Bash example invokes belt to retrieve tweet details from X. This is intended external command and network activity.
Medium
Ruby/shell backtick execution
```bash
The Bash example invokes belt to delete a specified tweet. This is an external command with a destructive account side effect.
Medium
Ruby/shell backtick execution
```bash
The workflow invokes a remote image-generation app, writes output to image.json, and posts media to X. It performs external commands with filesystem and public side effects.
Medium
Ruby/shell backtick execution
```bash
The workflow invokes a remote video-generation app, writes output to video.json, and posts media to X. It has filesystem, network, and public account effects.
Medium
Ruby/shell backtick execution
```bash
The Bash block runs four unpinned npx installation commands for remote skills. Executing them introduces code and instruction supply-chain exposure.
Low
Hardcoded URL
. [Install instructions](https://raw.githubusercontent.com/infer
The link directs users to installation instructions on a mutable raw GitHub branch. Following those instructions introduces an external trust and supply-chain dependency.
Risk Factors
⚙️ External commands (37)
SKILL.md:7 SKILL.md:17 SKILL.md:19-24 SKILL.md:24-31 SKILL.md:31-32 SKILL.md:32-33 SKILL.md:33-34 SKILL.md:34-35 SKILL.md:35-36 SKILL.md:36-37 SKILL.md:37-38 SKILL.md:38-39 SKILL.md:39-45 SKILL.md:45-47 SKILL.md:47-51 SKILL.md:51-61 SKILL.md:61-65 SKILL.md:65-67 SKILL.md:67-71 SKILL.md:71-73 SKILL.md:73-77 SKILL.md:77-82 SKILL.md:82-86 SKILL.md:86-88 SKILL.md:88-92 SKILL.md:92-94 SKILL.md:94-98 SKILL.md:98-100 SKILL.md:100-104 SKILL.md:104-106 SKILL.md:106-110 SKILL.md:110-119 SKILL.md:119-123 SKILL.md:123-132 SKILL.md:132-136 SKILL.md:136-148 SKILL.md:148-150
🌐 Network access (7)
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/infsh-skills-twitter-automation/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/infsh-skills-twitter-automation?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/infsh-skills-twitter-automation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/infsh-skills-twitter-automation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/infsh-skills-twitter-automation.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
infsh-skills. (2026). twitter-automation security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/infsh-skills-twitter-automation/audits/5BibTeX citation
@techreport{infsh-skills-infsh-skills-twitter-automation-2026,
author = {infsh-skills},
title = {twitter-automation security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/infsh-skills-twitter-automation/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "twitter-automation security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "infsh-skills"
date-released: "2026-08-06"
url: "https://skillstore.io/skills/infsh-skills-twitter-automation/audits/5"
identifiers:
- type: other
value: "skillstore:infsh-skills-twitter-automation:audit:5"
description: "Skillstore immutable audit report identifier"
Compare variants
16 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
sickn33 Recommended
sickn33-twitter-automation
Skillstore Score 70
Evidence Confidence High
Skillstore usage 7
Updated
2026-08-21
inferen-sh-twitter-automation
Skillstore Score 69
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
skillssh-twitter-automation
Skillstore Score 50
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
infsh-skills Current
infsh-skills-twitter-automation
Skillstore Score 50
Evidence Confidence High
Skillstore usage 7
Updated
2026-08-21
skills-shell-twitter-automation
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
101-skills-twitter-automation
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
qu-skills-twitter-automation
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 4
Updated
2026-08-21
tul-sh-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated
2026-08-21
toolshell-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated
2026-08-21
inference-sh-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
inference-shell-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
inference-sh-8-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
halt-catch-fire-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
inference-skills-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
inference-sh-skills-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
inference-sh-9-twitter-automation
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 4
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
68
Community
91
Spec Compliance
What You Can Build
Publish Campaign Updates
Prepare and publish reviewed text or media updates from a repeatable command workflow.
Share Product Releases
Post concise release announcements and retrieve the resulting post for verification.
Manage Community Responses
Retrieve profiles and send approved direct responses to known community members.
Try These Prompts
Draft a Text Post
Draft one X post about [topic] for [audience]. Keep it under [limit] characters and wait for my approval before publishing.
Publish Approved Media
Prepare an X post using this approved text: [text]. Attach media from [media URL], show the final content, and request confirmation.
Review a Target Before Engagement
Retrieve the X profile for [username] and summarize relevant public details. Do not follow, message, like, or retweet without separate approval.
Coordinate a Controlled Release Workflow
Create a release workflow for [announcement]. Generate media, prepare the post, validate identifiers and links, and require confirmation before every external action.
Best Practices
- Review the target account, post content, links, and media before every external action.
- Use explicit confirmation for publishing, deletion, direct messages, follows, likes, and retweets.
- Respect X policies, recipient consent, rate limits, and organizational approval requirements.
Avoid
- Do not automate bulk follows, unsolicited messages, or repetitive engagement.
- Do not publish generated media before checking ownership, accuracy, and disclosure requirements.
- Do not place credentials, private data, or confidential content in command inputs.
Frequently Asked Questions
What setup does this skill require?
It requires the belt CLI, an inference.sh account, and a working X integration.
Can it publish posts with media?
Yes. The x/post-create app accepts post text and a media URL for an image or video.
Does it schedule posts?
No scheduling command is documented. Use an external scheduler or an approved orchestration system.
Can it delete a post?
Yes. The x/post-delete app deletes a post by identifier and should require explicit confirmation.
Can it send direct messages or follow users?
Yes. Use these actions only for approved recipients and accounts, with consent and rate limits.
Does it provide analytics or moderation?
No. The documented apps cover account actions and retrieval, not analytics, moderation, or campaign reporting.
Developer Details
Author
infsh-skillsLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
4121de961d1b6f2ffca856260e239505c302452c
Maintenance freshness
8/7/2026
Usage
5 downloads · 70 views
File structure
📄 SKILL.md