Skills twitter-automation
📦

twitter-automation

Content revision r1 Critical ⚙️ External commands🌐 Network access

Automate Twitter/X Posts and Engagement

Managing Twitter/X actions from an AI assistant can be slow and error-prone. This skill provides inference.sh commands for approved posts, media posts, engagement, DMs, follows, and lookups.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

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-sh-9-twitter-automation.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-twitter-automation/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

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.

Markdown detail GET /skills/inference-sh-9-twitter-automation.md Signed manifest GET /api/skills/inference-sh-9-twitter-automation/manifest Signed lockfile GET /api/skills/inference-sh-9-twitter-automation/lockfile

Test it

Using "twitter-automation". Post this approved product announcement to X.

Expected outcome:

  • Confirms the target account and post text.
  • Publishes the update through the text post app.
  • Reports the resulting post ID or link when available.

Using "twitter-automation". Send a thank-you DM to this confirmed recipient.

Expected outcome:

The assistant asks for recipient confirmation, sends the message through the DM app, and reports delivery status.

Using "twitter-automation". Create an image post from this approved media URL.

Expected outcome:

The assistant submits the media post, then records the final post details for review.

Security Audit

Critical
v4 • 7/6/2026 Open versioned report

Several static backtick findings are Markdown-only false positives, but multiple fenced examples do invoke external commands for Twitter/X account actions. The quick start contains a confirmed critical curl-to-shell installer pattern. Semantic review also found social engagement abuse risk because DMs, follows, likes, and retweets lack consent, rate-limit, or approval guidance.

1
Files scanned
155
Lines analyzed
14
Review items
0
False positives ignored

Confirmed security concerns (2)

Critical
SKILL.md:17
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh && infsh login
The quick start pipes a remote installer directly into sh, then continues to login. This executes network-delivered code before the user can inspect it.
High
SKILL.md:3SKILL.md:31-36SKILL.md:73-85
Automated Social Engagement Abuse
The skill advertises engagement bots and audience growth, then provides actions for likes, retweets, DMs, follows, and deletes. Without approval, consent, or rate-limit guidance, it can enable spam, impersonation, or platform-policy abuse.
The skill explicitly promotes engagement automation and includes examples for DMs, follows, likes, and retweets. No countervailing safeguards or approval requirements are present in the cited lines.
Capability review items (14)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Critical
SKILL.md:17
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh && infsh login
The hardcoded URL is used as the source for a curl-to-shell installer on the same line. That makes the network dependency part of an executable code path.
High
SKILL.md:15-21
Ruby/shell backtick execution
```bash
This fenced shell example includes a remote installer piped to sh and an infsh command. The Markdown backtick is harmless, but the mapped block gives executable shell instructions.
High
SKILL.md:75-80
Ruby/shell backtick execution
```bash
This block contains an infsh command that sends a direct message. It can contact another user through the account, so misuse could create spam or social-engineering risk.
High
SKILL.md:102-104
Ruby/shell backtick execution
```bash
This block contains an infsh command that deletes a post by ID. That is a destructive account action if run against a real account.
High
SKILL.md:134-146
Ruby/shell backtick execution
```bash
This block shows npx commands to install related skills from a package source. Running package-manager commands can execute third-party code and should require review.
Medium
SKILL.md:43-45
Ruby/shell backtick execution
```bash
This block contains an executable infsh command that posts to Twitter/X. The command is hardcoded, but it can perform a networked account action when run.
Medium
SKILL.md:49-59
Ruby/shell backtick execution
```bash
This block invokes infsh to sample and submit a media post request. It is expected functionality, but it still executes an external CLI with account effects.
Medium
SKILL.md:63-65
Ruby/shell backtick execution
```bash
This block contains an infsh command that likes a post. It can change account state on Twitter/X when executed.
Medium
SKILL.md:69-71
Ruby/shell backtick execution
```bash
This block contains an infsh command that retweets a post. It can publish account engagement on Twitter/X when executed.
Medium
SKILL.md:84-86
Ruby/shell backtick execution
```bash
This block contains an infsh command that follows a user. It can change account relationships on Twitter/X when executed.
Medium
SKILL.md:90-92
Ruby/shell backtick execution
```bash
This block contains an infsh command that queries a user profile. The command is fixed, but it still invokes an external networked CLI.
Medium
SKILL.md:96-98
Ruby/shell backtick execution
```bash
This block contains an infsh command that retrieves post details. The command is fixed, but it still invokes an external networked CLI.
Medium
SKILL.md:108-117
Ruby/shell backtick execution
```bash
This workflow runs external generation and posting commands, including redirecting output to a local file. It is intended behavior but expands external command and network exposure.
Medium
SKILL.md:121-130
Ruby/shell backtick execution
```bash
This workflow runs external video generation and posting commands, including redirecting output to a local file. It is intended behavior but expands external command and network exposure.

Risk Factors

⚙️ External commands (36)
SKILL.md:15-21 SKILL.md:21-23 SKILL.md:23-29 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 (8)
SKILL.md:9 SKILL.md:11 SKILL.md:17 SKILL.md:23 SKILL.md:55 SKILL.md:152 SKILL.md:153 SKILL.md:154

Detected Patterns

Pipe to shell pattern
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.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/inference-sh-9-twitter-automation/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-9-twitter-automation/security.svg)](https://skillstore.io/skills/inference-sh-9-twitter-automation?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-9-twitter-automation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-twitter-automation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-9-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-sh-9. (2026). twitter-automation security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-twitter-automation/audits/4

BibTeX citation

@techreport{inference-sh-9-inference-sh-9-twitter-automation-2026, author = {inference-sh-9}, title = {twitter-automation security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/inference-sh-9-twitter-automation/audits/4}, 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 4)" version: "unspecified" type: report authors: - name: "inference-sh-9" date-released: "2026-07-06" url: "https://skillstore.io/skills/inference-sh-9-twitter-automation/audits/4" identifiers: - type: other value: "skillstore:inference-sh-9-twitter-automation:audit:4" description: "Skillstore immutable audit report identifier"

Compare variants

16 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
sickn33 Recommended

sickn33-twitter-automation

Skillstore Score 70
Evidence Confidence High
Skillstore usage 7
Updated

2026-08-21

inferen-sh

inferen-sh-twitter-automation

Skillstore Score 69
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

skillssh

skillssh-twitter-automation

Skillstore Score 50
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

infsh-skills

infsh-skills-twitter-automation

Skillstore Score 50
Evidence Confidence High
Skillstore usage 7
Updated

2026-08-21

skills-shell

skills-shell-twitter-automation

Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

101-skills

101-skills-twitter-automation

Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

qu-skills

qu-skills-twitter-automation

Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 4
Updated

2026-08-21

tul-sh

tul-sh-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated

2026-08-21

toolshell

toolshell-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated

2026-08-21

inference-sh

inference-sh-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated

2026-08-21

inference-shell

inference-shell-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated

2026-08-21

halt-catch-fire

halt-catch-fire-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated

2026-08-21

inference-sh-8

inference-sh-8-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated

2026-08-21

inference-skills

inference-skills-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

inference-sh-skills

inference-sh-skills-twitter-automation

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated

2026-08-21

inference-sh-9 Current

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
69
Community
83
Spec Compliance

What You Can Build

Publish Approved Updates

Prepare controlled product updates and publish approved text or media posts from an AI assistant.

Test X Integrations

Validate an inference.sh X integration by posting, reading, and deleting controlled test tweets.

Coordinate Creator Posts

Draft media posts and run selected account actions after manual review and approval.

Try These Prompts

Post a Simple Update 
Use the twitter-automation skill to publish this approved update to X: [text]. Confirm the account before posting.
Create a Media Post 
Create an X post with this approved text and media URL: [text] and [media URL]. Ask before running the command.
Review a Post Action 
Use the skill to retrieve post [post ID], summarize its details, and ask before deleting, liking, or retweeting it.
Plan a Controlled Campaign 
Plan a three-post workflow using approved text, media URLs, and confirmation checkpoints. Run only the approved X actions.

Best Practices

  • Review every post, DM, follow, like, retweet, and delete action before execution.
  • Use test accounts or draft text when validating integration setup.
  • Install the inference.sh CLI through a reviewed, checksum-verified method.

Avoid

  • Do not pipe remote install scripts to a shell without inspection.
  • Do not run bulk likes, follows, retweets, or DMs without consent and rate limits.
  • Do not post generated media without checking rights, accuracy, and account context.

Frequently Asked Questions

Does this skill post directly to X?
Yes. It uses inference.sh X app commands to create text posts and media posts after setup.
What setup is required?
You need the inference.sh CLI, an active login, and a configured X integration.
Can it send DMs or follow users?
Yes. The skill lists direct message and follow actions, which should always require explicit approval.
Does it include safety controls?
No built-in consent, rate-limit, or approval system is documented in the skill file.
Why is the installer risky?
The quick start pipes a remote script to a shell. Review the script and verify checksums before installation.
Can it schedule tweets?
The description mentions scheduling, but no dedicated scheduling command is shown in SKILL.md.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh-9/skills/tree/main/skills/twitter-automation/

Ref

a06681402992ceae98ba04d54cfd4ab004862696

Maintenance freshness

7/18/2026

Usage

2 downloads · 166 views

File structure

📄 SKILL.md