seo-on-page-optimization
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external URLs through various MCP analysis tools, creating a potential vector for indirect prompt injection.
- Ingestion points:
CHECKLISTS.mdandSKILL.mddefine workflows that process remote content viaanalyze_pageand related tools. - Boundary markers: There are no explicit instructions or delimiters provided within the skill to mitigate the risk of instructions embedded in the analyzed web pages.
- Capability inventory: The skill utilizes tools for reading page content and structure but does not include file system modifications or arbitrary command execution.
- Sanitization: The skill does not provide methods for sanitizing or validating external content before processing.
Audit Metadata