seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
beltCLI vianpx skills add belt-sh/cliand refers to documentation hosted onraw.githubusercontent.com/inference-sh/. These are well-known services and repositories related to the skill's infrastructure and are considered safe practice for skill setup. - [COMMAND_EXECUTION]: Several examples use the
beltCLI tool (e.g.,belt login,belt app run). These commands are intended for interacting with the vendor's SEO and search tools and do not involve unauthorized system access or dangerous shell operations. - [INDIRECT_PROMPT_INJECTION]: The skill ingests search results from external APIs (Tavily and Exa) to generate content briefs. While this represents a data ingestion surface, the risk is mitigated as the skill primarily guides the user/agent in structuring marketing data rather than executing code based on the retrieved content. Use of standard boundary markers in the content brief template follows best practices.
Audit Metadata