Typecho Post Publisher

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  1.0.0

Overview

This skill is designed to publish and edit a real Typecho blog using stored credentials, but it lacks clear confirmation and credential-scope safeguards before making public changes.

Review before installing. Use a dedicated low-privilege Typecho account where possible, avoid storing a full admin password if you can, and require the agent to show the target blog, title, content summary, category, and whether it is creating or editing before any publish or save action.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill explicitly automates logging into a Typecho admin panel and publishing or editing content using stored credentials, but it does not warn the user that the agent may use preconfigured blog credentials to access an administrative interface and modify site content. This creates a consent and transparency gap: a user may invoke the skill without understanding it can perform privileged actions on their blog, increasing the risk of unintended publication, unauthorized edits, or misuse of stored secrets.

VirusTotal

65/65 vendors flagged this skill as clean.