The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run standard development and build commands such as npm run build, astro check, and bin/rails test. These are legitimate operations used to verify the integrity and successful generation of the landing pages created by the skill.- [EXTERNAL_DOWNLOADS]: The skill integrates with several well-known SEO and research services, including Exa, Firecrawl, and Ahrefs. These integrations are documented and necessary for the keyword research and SERP analysis phases of the SEO workflow.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web (via search results and competitor site analysis). While this is a known attack surface, the risk is mitigated by the skill's use of strict data schemas (TypeScript interfaces) and structured templates for generating output, which prevents the agent from executing instructions embedded in the crawled content.- [DATA_EXPOSURE]: The skill reads project configuration files and brand positioning documents to tailor its SEO strategy. This access is required for its primary function and follows standard practices for AI agents operating within a local repository. No evidence of sensitive credential harvesting (e.g., SSH keys or cloud credentials) was found.

seo-machine