seo-technical
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external websites based on user-provided URLs. This creates a surface where malicious content on the target website could attempt to influence the agent's behavior.
- Ingestion points: The skill processes external HTML, accessibility trees, and SEO metadata from URLs provided in the
[url]argument. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the retrieved web content are defined.
- Capability inventory: The skill executes Python scripts for rendering and audit scoring, and utilizes external SEO tools and APIs.
- Sanitization: No specific content sanitization or filtering is mentioned for the ingested web data.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local Python scripts (e.g.,
agent_ux_check.py,render_page.py,pagespeed_check.py) to perform rendering and analysis tasks. - [EXTERNAL_DOWNLOADS]: The skill references documentation and guidelines from Google's official developer portal for AI optimization and search fundamentals.
Audit Metadata