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_search MCP tool.
  • Sanitization: No explicit filtering or sanitization of ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 09:13 AM
Security Audit — agent-trust-hub — seo-local