seo-local
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were found. The skill is purely instructional and follows SEO industry best practices.- [PROMPT_INJECTION]: The skill processes untrusted data from user-provided URLs, which is a known surface for indirect prompt injection (Category 8). As the primary purpose of the skill is web content analysis, this is an inherent functional risk rather than a malicious intent.
- Ingestion points: Target website HTML, schema JSON-LD, and review data processed via web-reading capabilities.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the analyzed data.
- Capability inventory: The agent reads external pages and potentially uses the
business_data_business_listings_searchMCP tool. - Sanitization: No explicit filtering or sanitization of ingested content is specified.
Audit Metadata