The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run external Python management scripts (manage_markdown_site.py and manage_markdown_work.py) to automate SEO roadmap tasks and site builds.
[DYNAMIC_EXECUTION]: Script execution relies on resolving a <suite-root> path at runtime from a local configuration file (.seo-suite-runtime.json) or environment variables. This creates a dependency on an external suite of tools whose integrity is not verified within the skill's instructions.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of SEO audit artifacts and research findings to generate roadmaps. It lacks robust security measures to prevent malicious instructions embedded in these inputs from influencing the agent's behavior. 1. Ingestion points: External SEO research artifacts, audit findings, and inventory.json. 2. Boundary markers: No explicit delimiters or warnings are used to isolate untrusted evidence from the agent's instructions. 3. Capability inventory: Execution of Python scripts for file management and site generation. 4. Sanitization: No input validation or sanitization protocols are defined for the ingested SEO data.

seo-plan