twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official tools and commands from the author 'inference-shell'. All commands and tool references are consistent with the vendor's ecosystem.
- [EXTERNAL_DOWNLOADS]: The skill documentation references installing additional skills via
npx skills add inference-sh/skills@agent-tools, which is a standard procedure for expanding the agent's capabilities within the vendor's ecosystem. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves data from external sources using
tavily/search-assistantandinfsh/agent-browser. This data is subsequently used to generate content forx/post-create. Ingestion points: External search results and web browser content. Boundary markers: None observed in the prompt templates. Capability inventory: Ability to post content to Twitter/X viax/post-create. Sanitization: No specific sanitization or validation of the untrusted web data is defined before the content is prepared for posting.
Audit Metadata