seo
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze external data from user-provided URLs, creating a surface for potential injection from malicious website content.
- Ingestion points: Untrusted website data is ingested through commands such as
/seo audit <url>,/seo page <url>, and/seo technical <url>. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when the agent processes retrieved web content.
- Capability inventory: The skill orchestrates multiple subagents and sub-skills that perform network data retrieval, technical audits, and schema generation.
- Sanitization: No explicit sanitization, filtering, or validation logic is defined for handling the external content before it is processed by the agent.
Audit Metadata