claude-code-seo-content-marketing-suite
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation guide recommends cloning a repository from a personal, unverified GitHub account (
PrefectFlourish22/r18-anthropics-claude-code-seo). This introduces a supply chain risk as the implementation logic is hosted outside of trusted organizations or well-known services. - [INDIRECT_PROMPT_INJECTION]: The suite is designed to crawl and analyze external web content via commands like
/content-audit,/technical-seo, and/page-speed-seo. - Ingestion points: External website content, HTML metadata, and sitemap XML files (as described in the command documentation in
SKILL.md). - Boundary markers: The skill does not define any delimiters or safety instructions to prevent the agent from potentially following instructions embedded within the analyzed web pages.
- Capability inventory: The skill performs network requests to arbitrary domains and processes the returned data.
- Sanitization: There is no description of sanitization, filtering, or escaping applied to the external content before the agent analyzes it.
Audit Metadata