blog-post
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill is strictly scoped to a specific local project directory (/Users/espen/Dev/e9n.dev/) for the purpose of drafting and editing blog posts. It does not attempt to access sensitive system paths, credentials, or environment variables.
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands to list directory contents and run a local development server (npm run dev). These operations are consistent with the skill's primary purpose of managing and previewing a web project.
- [DATA_EXPOSURE]: The skill reads local markdown files to ensure stylistic consistency. There is no evidence of data exfiltration or network operations targeting external domains.
- [SAFE]: While the skill ingests data from local files which could theoretically contain instructions (Indirect Prompt Injection surface), the data source is the user's own development repository, and the skill includes no mechanisms for data exfiltration that would make such an injection actionable.
Audit Metadata