Versioned security assessment

Report ID: SA-9F814FC6

7/7/2026, 3:07:33 AM

twitter-automation security assessment v3

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
twitter-automation
Version
v3
Maintainer
sickn33
Source
github.com/sickn33/antigravity-awesome-skills/tree/main/skills/twitter-automation
Coverage
1 Files scanned · 232 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 static findings are false positives caused by Markdown backticks around Rube and Twitter tool names, not executable code. The hardcoded Rube MCP endpoint is a real external network dependency, and the skill enables authenticated public posting and destructive account actions. No prompt injection text was found in SKILL.md.

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 · 232 Lines analyzed

2 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 1 evidence location

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 71 evidence locations

Capability review items (1)
Low
SKILL.md:20
Hardcoded URL
**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API k
The skill instructs users to connect to the hardcoded remote MCP endpoint https://rube.app/mcp. This is an intentional external network dependency and third-party trust boundary, not evidence of malicious exfiltration.

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:34-39SKILL.md:202-204
Authenticated Social Account Actions Need Confirmation
The skill guides agents to create and delete posts through an authenticated Twitter/X account. It also notes that retries can create duplicate posts, but it does not require final user approval before public or destructive actions.
The create and delete workflow is explicit, and the non-idempotency warning confirms duplicate public posts are possible. The risk is contextual because legitimate automation is intended.

Remediation

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

  1. FIX-001
    Medium
    No explicit confirmation before public or destructive actions
    Require final user confirmation before publishing, deleting, unbookmarking, or unliking account content.
  2. FIX-002
    Medium
    Non-idempotent post creation can duplicate public posts
    Add retry guidance that checks recent posts or stores an operation marker before retrying post creation.
  3. FIX-003
    Low
    Remote MCP endpoint and OAuth trust boundary
    Document that users should verify the Rube MCP endpoint and Twitter OAuth scopes before connecting an account.

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