seo-audit

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides detailed instructions for using the ghost-cli tool to perform metadata updates, social card configuration, and schema injection on Ghost CMS websites. These commands are integral to the skill's primary function of optimizing site visibility.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze content from external URLs to provide SEO recommendations.
  • Ingestion points: Website content and metadata fetched via curl or agent browser tools.
  • Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the analyzed content.
  • Capability inventory: The skill uses ghost-cli to perform write operations (metadata updates) to the target CMS.
  • Sanitization: No specific content sanitization or validation logic is detailed for the data being processed from the web.
  • [DATA_EXPOSURE]: The documentation references the Ghost Admin API and technical requirements for updating posts, such as including the updated_at timestamp for optimistic locking. No hardcoded credentials or sensitive local file paths were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:03 PM
Security Audit — agent-trust-hub — seo-audit