linkedin-content
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides educational content, including hook formulas and formatting guidelines for professional social media posts.\n- [EXTERNAL_DOWNLOADS]: The skill includes instructions to install platform-specific CLI tools and references official documentation hosted on GitHub by the service provider.\n- [INDIRECT_PROMPT_INJECTION]: The skill encourages using a search assistant to research trending content, which creates a surface for potential indirect prompt injection from external web search results.\n
- Ingestion points: Research results from
tavily/search-assistantsuggested inSKILL.md.\n - Boundary markers: No specific delimiters or boundary markers for external data are included in the provided examples.\n
- Capability inventory: The skill utilizes
belt app runfor research, cross-posting to social media, and image generation.\n - Sanitization: No explicit sanitization or filtering of external content is demonstrated in the skill's instructions.
Audit Metadata