The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to run a series of specialized SEO audit scripts (e.g., sitemap_discovery.py, agent_ux_check.py) using a local wrapper utility claude-seo located in the environment's plugin root directory.
[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves crawling and interpreting content from external URLs (HTML, robots.txt, sitemaps). This creates a vulnerability where malicious instructions hosted on external sites could be ingested and acted upon by the agent.
Ingestion points: Content retrieved from external URLs via fetch_page.py, render_page.py, and other audit tools.
Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to treat external content as untrusted data.
Capability inventory: The skill uses subprocess execution for audits and has network access to fetch external resources.
Sanitization: No specific sanitization or validation logic is defined for the content fetched during the audit process.
[PRIVILEGE_ESCALATION]: The skill provides instructions for utilizing an environment variable, CLAUDE_SEO_LOCAL_TARGETS, to override the default security policy that prevents the agent from accessing loopback and private network addresses. This enables the agent to interact with internal services that are typically restricted.

seo-technical