📦
web-search
70Search and Extract Web Research
Finding current web evidence can slow down research and agent workflows. This skill runs Tavily and Exa searches through belt for sourced answers and extracted content.
Research & Learning View
Skills twitter-automation
📦
twitter-automation
Content revision r1 High Risk ⚙️ External commands🌐 Network access
Automate Twitter/X Actions
Managing Twitter/X tasks manually slows down social media workflows. This skill gives Claude, Codex, and Claude Code guided commands for posting, engagement, messages, and profile lookups through inference.sh.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
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/inference-skills-twitter-automation.md and its manifest at https://skillstore.io/api/skills/inference-skills-twitter-automation/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.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". Post a short update about our new API documentation.
Expected outcome:
The assistant drafts a concise tweet, shows the belt command that will publish it, and asks for confirmation before posting.
Using "twitter-automation". Get the profile for OpenAI.
Expected outcome:
The assistant runs the profile lookup command and returns key profile details without taking any engagement action.
Using "twitter-automation". Share this image URL with a caption.
Expected outcome:
The assistant prepares a media post command using the supplied URL and asks the user to approve the exact caption and media link.
Security Audit
High Riskv6 • 7/9/2026 Open versioned report
The markdown backtick detector produced many false positives on tables and code-fence markers, but several shell examples are real external commands that can post, delete, like, retweet, DM, follow users, and install remote skills. Hardcoded URLs are mostly documentation or examples, while the main concern is broad CLI authority over a Twitter/X account and potential social platform abuse.
1
Files scanned
156
Lines analyzed
13
Review items
0
False positives ignored
Confirmed security concerns (2)
High
Broad Twitter/X Account Action Permission
The skill declares allowed-tools: Bash(belt *) and then documents commands for posting, deleting posts, liking, retweeting, sending DMs, and following users. This grants broad account-changing capability through one CLI namespace, so accidental or malicious prompts could perform visible social actions if the user approves the skill.
The permission and documented app list directly show broad remote account actions. The risk is contextual rather than a single syntax pattern.
Medium
Potential Social Platform Abuse Workflows
The skill description explicitly lists engagement bots and audience growth, while examples include liking, retweeting, DMs, and following users. These capabilities can support spam or unwanted outreach if used without strict user confirmation and platform-policy checks.
The stated use cases and examples clearly include engagement automation. Legitimate social media management is possible, but abuse risk is inherent in the documented workflows.
Capability review items (13)
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
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
The fenced bash example runs belt commands that perform external Twitter/X or inference.sh actions. These commands can change account state, send messages, post content, or create media-backed posts.
Medium
Ruby/shell backtick execution
```bash
This block instructs users to run npx skills add commands that fetch and install remote community skills. That is real external command execution with supply-chain impact, even though the commands are documented examples.
Risk Factors
⚙️ External commands (36)
SKILL.md:15 SKILL.md:17-22 SKILL.md:22-29 SKILL.md:29-30 SKILL.md:30-31 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:37-43 SKILL.md:43-45 SKILL.md:45-49 SKILL.md:49-59 SKILL.md:59-63 SKILL.md:63-65 SKILL.md:65-69 SKILL.md:69-71 SKILL.md:71-75 SKILL.md:75-80 SKILL.md:80-84 SKILL.md:84-86 SKILL.md:86-90 SKILL.md:90-92 SKILL.md:92-96 SKILL.md:96-98 SKILL.md:98-102 SKILL.md:102-104 SKILL.md:104-108 SKILL.md:108-117 SKILL.md:117-121 SKILL.md:121-130 SKILL.md:130-134 SKILL.md:134-146 SKILL.md:146-148
🌐 Network access (7)
Audited by: claude 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/inference-skills-twitter-automation/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-skills-twitter-automation?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-skills-twitter-automation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-skills-twitter-automation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-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
inference-skills. (2026). twitter-automation security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-skills-twitter-automation/audits/6BibTeX citation
@techreport{inference-skills-inference-skills-twitter-automation-2026,
author = {inference-skills},
title = {twitter-automation security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/inference-skills-twitter-automation/audits/6},
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 6)"
version: "unspecified"
type: report
authors:
- name: "inference-skills"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/inference-skills-twitter-automation/audits/6"
identifiers:
- type: other
value: "skillstore:inference-skills-twitter-automation:audit:6"
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-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
halt-catch-fire-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
inference-skills Current
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: Medium 55
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance
What You Can Build
Publish product updates
Prepare and post concise launch updates or feature announcements from a terminal workflow.
Share generated media
Create an image or video with inference.sh apps and post the resulting media URL to Twitter/X.
Review account interactions
Retrieve post details or user profiles before deciding whether to engage from an authorized account.
Try These Prompts
Post a simple update
Use the twitter-automation skill to post this update after showing me the exact command: <tweet text>.
Create a media post
Use the Twitter/X automation skill to create a post with this text and media URL. Ask for confirmation before running it.
Check a user before engaging
Get the Twitter/X profile for <username> and summarize the result. Do not follow or message the user unless I confirm.
Build a guarded posting workflow
Generate media with inference.sh, draft a Twitter/X post, show the final text and media URL, then wait for my approval before posting.
Best Practices
- Preview every post, DM, follow, like, retweet, or delete action before running it.
- Use authorized accounts and follow Twitter/X platform rules for automation and outreach.
- Keep credentials and integration setup outside prompts and command examples.
Avoid
- Do not run bulk engagement, spam, or unsolicited DM campaigns.
- Do not post generated media without checking ownership, consent, and accuracy.
- Do not install related skills or remote packages without verifying the source.
Frequently Asked Questions
Does this skill post directly to Twitter/X?
Yes. It uses inference.sh belt commands that can publish posts when the account integration is configured.
Can it send direct messages?
Yes. The skill documents an x/dm-send command that sends a message to a recipient ID.
Does it support images or videos?
Yes. It uses x/post-create with a media URL and includes workflows for generated images and videos.
Do I need an inference.sh account?
Yes. The examples require the belt CLI and a login before commands can run.
Is this safe for automated engagement?
Use caution. The skill can like, retweet, DM, and follow, so every action should require explicit review.
Can Claude Code use this skill?
Yes. The report lists Claude, Codex, and Claude Code as supported tools.
Developer Details
Author
inference-skillsLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
1ffa7643651792ccb4bd3b15d924d2c97edff755
Maintenance freshness
7/18/2026
Usage
2 downloads · 93 views
File structure
📄 SKILL.md
More from inference-skills
View all📦
ai-image-generation
69Generate AI Images with Inference.sh
Image teams need quick access to many generation and editing models without writing provider-specific workflows. This skill supplies belt CLI examples for text-to-image, edits, upscaling, and model selection.
Design & Creative View
📦
ai-avatar-video
69Create AI Avatar Videos
Producing talking head videos often requires editing tools, voice generation, and model selection. This skill gives Claude, Codex, and Claude Code CLI workflows for avatar video generation.
Design & Creative View
📦
ai-video-generation
69Create AI Videos with Inference.sh
Video teams need fast access to many AI video models without memorizing each provider API. This skill guides Claude, Codex, and Claude Code through inference.sh belt commands for generation, editing, upscaling, and audio workflows.
Design & Creative View
📦
remotion-render
50Render Remotion Videos From React Code
Teams need fast video previews from React animation code without managing a local Remotion setup. This skill sends TSX to inference.sh and returns rendered MP4 outputs.
Design & Creative View
📦
agent-tools
38Run Inference.sh AI Apps from Agents
Agents often need a consistent way to find and run hosted AI apps. This skill teaches the inference.sh CLI workflow for discovery, inputs, execution, and task results.
Productivity View
Related Skills
View all📦
lark-event
79Stream Lark Events for Real-Time Workflows
by larksuite
Real-time Lark workflows need reliable event streams, filtering, and clean shutdown behavior. This skill guides AI agents through bounded event consumption with lark-cli.
Communication View
📦
social
79Create Better Social Media Content
by coreyhaines31
Planning effective social content across platforms requires consistent formats, voice, and measurement. This skill provides practical frameworks for creation, repurposing, listening, and optimization.
Communication View
📦
content-creator
88Create SEO Content With Brand Voice
by alirezarezvani
Marketing teams need consistent content that fits each channel and supports search goals. This skill combines brand voice guidance, content templates, SEO checks, and social media planning.
Writing & Content View
📦
viral-short-form
87Write Short-Form Videos That Hold Attention
by vyralcontent
Short-form teams often lose time turning rough ideas into strong hooks and scripts. This skill creates hook sets, scripts, carousels, and critiques for major platforms.
Writing & Content View
📦
lark-doc
87Manage Lark Docs and Feishu Wiki Content
by larksuite
Teams need reliable document updates without switching between tools. This skill guides Claude, Codex, and Claude Code through authenticated lark-cli workflows for Lark Docs.
Office & Reports View
📦
pptx
85Create PowerPoint Presentations with Python
by AutumnsGrove
Building polished PowerPoint decks by hand is slow and hard to repeat. This skill guides Claude, Codex, and Claude Code through PPTX creation, editing, and automation with python-pptx.
Office & Reports View