twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the
belt-sh/clitool and provides a link to documentation hosted on GitHub (inference-sh/skills). These are standard dependencies for the platform's execution environment and originate from the service provider's official repositories. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-generated content is ingested and processed for publication on social media.
- Ingestion points: User input provided to the
textfield in variousbelt app run x/post-createcommands within SKILL.md. - Boundary markers: Use of JSON structure to delimit input data within the CLI commands.
- Capability inventory: The skill utilizes the
Bashtool to executebeltcommands which perform network API calls for posting content and browser actions for taking screenshots. - Sanitization: Content is handled by the platform's CLI application; the skill relies on the underlying tool for appropriate content processing.
Audit Metadata