seo-content-brief
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches installation instructions and adds related skill modules from the official inference.sh GitHub repository and package registry. These resources originate from the official ecosystem associated with the skill's functionality.
- [COMMAND_EXECUTION]: Utilizes the 'infsh' CLI for keyword research and SERP analysis. Shell access is explicitly restricted to this command via the skill's configuration, ensuring the agent cannot execute arbitrary system commands.
- [PROMPT_INJECTION]: As an SEO research tool, it ingests content from external websites via search tools to generate briefs. This creates a surface for indirect prompt injection where instructions hidden on web pages could influence the agent's output. Ingestion points: 'tavily/search-assistant', 'exa/search', and 'tavily/extract' tools in SKILL.md. Boundary markers: Absent. Capability inventory: Uses platform-specific search and image tools; no unrestricted local shell or file-system write access. Sanitization: Not specified in instructions.
Audit Metadata