skills/fradser/dotclaude/ai-seo/Gen Agent Trust Hub

ai-seo

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed of purely instructional markdown files. There are no scripts, automated commands, or network operations performed by the skill itself. All links provided lead to well-known technical documentation (Google, llmstxt.org) or legitimate SEO tools.
  • [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to check for and read project context from files like .agents/product-marketing.md. This is a standard practice for personalizing agent output and does not constitute a risk within the provided instructions.
  • Ingestion points: Reads from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md in the project directory.
  • Boundary markers: No specific delimiters are mandated in the instructions.
  • Capability inventory: The skill references the use of standard SEO auditing tools (semrush, ahrefs, GSC, GA4).
  • Sanitization: Not applicable as the skill is an instructional framework rather than a processing script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:30 AM
Security Audit — agent-trust-hub — ai-seo