Leo X Post

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:23 PM UTC
• Version:
  1.0.0

Overview

This is a simple X/Twitter posting helper that is clear about posting through the X API, but users should review exactly what will be published before sending.

Install only if you intend to let an agent post through your X/Twitter account. Use limited, revocable API credentials and require a final review of the exact text, media, reply target, and schedule before publishing.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrase includes an ambiguous catch-all ('或类似'), which can cause the agent to invoke this skill on loosely related requests. Because this skill performs a live external posting action to X, overly broad triggering increases the risk of unintended publication of user content or attachments.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill description does not clearly warn users that using the skill causes a live network action that can publish content and attachments to a public external platform. In the context of a posting skill, missing this warning materially increases the chance of accidental disclosure, reputational harm, or unintended publication to a real audience.

VirusTotal

60/60 vendors flagged this skill as clean.