ai-seo
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection as it is designed to ingest external context from product marketing files and user-provided search queries.
- Ingestion points: The agent is instructed to read local files such as
.agents/product-marketing.mdto inform its analysis. - Boundary markers: The instructions do not specify the use of delimiters or specific safety markers for the ingested content.
- Capability inventory: No dangerous capabilities such as file-system writes, code execution, or network operations were identified in the skill's instructions.
- Sanitization: No specific content sanitization or validation logic is defined.
- [EXTERNAL_DOWNLOADS]: The skill provides references and links to external documentation and third-party SEO tools.
- References the
GoogleCloudPlatformorganization's repository for the Open Knowledge Format (OKF) specification, which is a well-known and trusted source. - Recommends several SEO monitoring platforms (Otterly AI, Peec AI, ZipTie) for users to track citation performance across different AI engines.
- All external links are for informational purposes or point to established SEO services.
Audit Metadata