seo-coach
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of natural language instructions to guide agent behavior as an SEO coach.
- [SAFE]: No hardcoded credentials, malicious scripts, or suspicious network operations were detected.
- [SAFE]: The skill references standard tool usage (MCP, Web Search, Scraping) as part of its documented functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest untrusted data from web search and browser scraping tools. This represents a standard attack surface for indirect prompt injection.
- Ingestion points: Web search and browser/page scraping mentioned in 'Tool coaching' section.
- Boundary markers: Absent.
- Capability inventory: Local file access, web search, and scraping tools mentioned in 'Tool coaching'.
- Sanitization: Not specified.
Audit Metadata