twitter-thread-creation

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides examples of using the belt CLI tool to perform tasks such as posting to X (x/post-create), generating images from HTML (infsh/html-to-image), and conducting web searches (tavily/search-assistant). These commands are integrated into the vendor's application ecosystem for social media management.
  • [EXTERNAL_DOWNLOADS]: Includes a link to installation guidelines hosted on the vendor's GitHub repository (raw.githubusercontent.com/inference-sh/skills). This is a standard documentation reference for setting up the required CLI environment.
  • [REMOTE_CODE_EXECUTION]: The skill mentions adding related modules via npx skills add. These are platform-specific commands for extending the agent's capabilities using official inference-sh packages.
  • [DATA_EXFILTRATION]: Although the skill can browse the web and post content externally, these capabilities are core to its functionality as a social media and research tool. No unauthorized data access or exfiltration patterns targeting sensitive system files or credentials were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 11:46 PM