seo-audit
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze content from external websites provided by the user.
- Ingestion points: Data enters the agent's context through tools like
web_fetch,curl, or browser-based rendering of external URLs (SKILL.md). - Boundary markers: The instructions do not include explicit delimiters or warnings to ignore potential instructions embedded within the audited website content.
- Capability inventory: The skill utilizes network fetch tools and reads specific local context files (
.agents/product-marketing-context.md). - Sanitization: There is no explicit mention of sanitizing or escaping the external content before processing.
- Note: This surface is inherent to the skill's primary function and is considered a low risk.
- [EXTERNAL_DOWNLOADS]: The skill references several official tools and documentation sources from well-known services, including Google Search Console, Bing Webmaster Tools, and established SEO platforms such as Semrush, Ahrefs, and Moz. These references are used for diagnostic and educational purposes.
Audit Metadata