twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
beltCLI for several legitimate tasks: posting tweets (belt app run x/post-create), performing research via Tavily (belt app run tavily/search-assistant), and generating thread-related visuals (belt app run infsh/html-to-image). These are within the scope of a social media content creation skill. - [EXTERNAL_DOWNLOADS]: Fetches installation instructions and related social media skills from the official
inference-shandbelt-shGitHub repositories. These are well-known services and trusted sources in the context of this ecosystem. - [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions focus on best practices for content formatting, structure, and engagement strategies.
Audit Metadata