boring-seo-audit

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill reads local brand strategy files from the world-code directory to personalize the SEO audit. This is a functional use of local storage for context.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it retrieves and analyzes content from external websites. Ingestion points: Site data fetched via web fetching tools. Boundary markers: None present in the instructions. Capability inventory: Network read access and local file reading. Sanitization: No specific sanitization of external HTML is described. This risk is inherent to the primary function of an SEO crawler and is not considered a malicious finding.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:28 PM