seo-content-brief
Warn
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install an external CLI tool ('infsh') from a remote GitHub repository (https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md).
- [COMMAND_EXECUTION]: The skill uses
npxto install and add external skill packages (e.g.,npx skills add inference-sh/skills@seo), which involves downloading and executing code from external sources. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from the web.
- Ingestion points: Data is retrieved via
tavily/search-assistant,exa/search, andtavily/extract(SKILL.md). - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the retrieved search results or extracted website content.
- Capability inventory: The skill utilizes the
infshBash tool to run various applications and search commands. - Sanitization: No evidence of sanitization or validation of the external content is provided before it is processed by the agent.
Audit Metadata