The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and analyze data from external websites.
Ingestion points: Commands such as /content-audit, /technical-seo, /competitor-gap, and /serp-monitor fetch and process data from user-specified external URLs and SERP results.
Boundary markers: The instructions do not define explicit boundary markers or safety prompts to prevent the agent from following instructions embedded within the analyzed website content.
Capability inventory: The skill has significant capabilities, including file system writes (--output, --export), network access to multiple third-party SEO and messaging APIs (Ahrefs, Semrush, Slack), and the ability to publish content to WordPress via API.
Sanitization: No evidence of sanitization, filtering, or escaping of the ingested external content is present in the provided documentation.
[COMMAND_EXECUTION]: The skill implements ten custom shell commands (e.g., /keyword-research, /content-audit, /technical-seo) that execute logic presumably contained within the cloned repository. It also supports automated workflows that chain these commands together.
[EXTERNAL_DOWNLOADS]: The installation instructions require cloning a repository from GitHub (https://github.com/RadianLayer41/r01-hesreallyhim-awesome-claude-code-seo.git) to the user's local machine to provide the skill's functionality.

radian-layer-41-seo-content-marketing-skill-suite