seo-page
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to analyze external URLs provided by users. This creates a surface where the agent ingests untrusted data from third-party websites.
- Ingestion points: Web content (HTML, meta tags, schema) fetched from user-provided URLs.
- Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore instructions embedded in the analyzed web content.
- Capability inventory: The skill itself contains no code, but the agent using it will perform network-read operations.
- Sanitization: Absent. There is no instruction to sanitize or filter the content before the LLM processes it for SEO metrics.
Audit Metadata