seo
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze content from external websites, including competitor domains and technical SEO files, which creates an attack surface for indirect prompt injection.
- Ingestion points: External website content (Phase 5), competitor domains (Phase 3), and technical files such as robots.txt and XML sitemaps (Phase 6).
- Boundary markers: The instructions do not include delimiters or specific guidance to help the agent distinguish between objective data and potential instructions embedded within the analyzed content.
- Capability inventory: The skill is primarily advisory and analytical, and does not demonstrate instructions for high-risk operations like shell command execution or sensitive file access.
- Sanitization: No procedures are specified for sanitizing or filtering content retrieved from external URLs before the agent processes it.
Audit Metadata