x-article-publisher

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The main publishing script scripts/publish_article.py uses subprocess.run() to execute other Python scripts within the skill package, such as parse_markdown.py and copy_to_clipboard.py. These calls are constructed using argument lists, which is a secure way to execute internal commands without risk of shell injection.- [CREDENTIALS_SAFE]: The skill implements a persistent authentication mechanism for X (Twitter) by storing browser session data and cookies locally in the data/browser_state/ directory. The documentation and project structure include measures to ensure these sensitive session files are not included in version control.- [EXTERNAL_DOWNLOADS]: The skill instructions guide the user to install standard Python dependencies including Pillow, pyobjc-framework-Cocoa, and patchright. These are established libraries required for the skill's functionality, such as image processing, clipboard interaction, and browser automation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 01:21 AM
Security Audit — agent-trust-hub — x-article-publisher