seo-sxo
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from the web, which constitutes an indirect prompt injection surface. \n
- Ingestion points: Target URLs are processed via
scripts/render_page.pyand search results are gathered via theWebSearchtool. \n - Boundary markers: The skill does not explicitly define delimiters to isolate external content from the execution context. \n
- Capability inventory: The agent can perform web searches and call DataForSEO API tools to retrieve data. \n
- Sanitization: There are no documented steps for filtering or sanitizing the retrieved HTML or search snippets before analysis. \n- [COMMAND_EXECUTION]: The skill execution pipeline relies on local Python scripts for page rendering and parsing. \n
- Evidence:
scripts/render_page.pyandscripts/parse_html.pyare invoked during the 'Target Acquisition' phase. \n - Context: These scripts are intended for parsing and rendering content as part of the SEO audit functionality and are not invoked with arbitrary or obfuscated parameters.
Audit Metadata