marketing-seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from target URLs or user-provided content to generate SEO reports, creating an indirect prompt injection surface. Ingestion points: Target URLs and user-provided website content (SKILL.md, Workflow Step 1). Boundary markers: Absent; the skill does not define specific delimiters for separating untrusted web content from instructions. Capability inventory: Audit reporting and narrative generation; no dangerous tools or subprocess commands are used. Sanitization: Not explicitly described.
- [EXTERNAL_DOWNLOADS]: The skill references official Naver services (smartplace.naver.com and searchad.naver.com) to provide business verification and advertising guidance. These references are to well-known official services and are utilized for their intended purpose within the SEO audit context.
Audit Metadata