seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as website content, crawl reports, and Search Console data. * Ingestion points: Site headers, XML sitemaps, robots.txt, and various SEO tool outputs (SKILL.md). * Boundary markers: There are no explicit instructions or delimiters defined to separate external data from agent instructions. * Capability inventory: The skill is primarily diagnostic and does not request specific tools for file modification or network exfiltration, which limits the potential impact of an injection. * Sanitization: The instructions do not define methods for sanitizing or escaping content retrieved from external sources.
Audit Metadata