skills/unifapi-agent/agents/seo-audit/Gen Agent Trust Hub

seo-audit

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the UnifAPI MCP server at mcp.unifapi.com to retrieve search engine results and website data. This connection is fundamental to the skill's auditing purpose and utilizes the vendor's official service.
  • [PROMPT_INJECTION]: The skill processes content from external websites provided by the user to perform SEO analysis. This functionality involves an inherent surface for indirect prompt injection. \n
  • Ingestion points: Web page content fetched via browser/html and browser/markdown in the auditing workflow. \n
  • Boundary markers: No specific delimiters are used to wrap the untrusted site content. \n
  • Capability inventory: The skill is strictly diagnostic and lacks the ability to execute code, write files, or access sensitive local credentials. \n
  • Sanitization: No explicit content filtering is performed on the data retrieved from the web.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 04:06 PM
Security Audit — agent-trust-hub — seo-audit