The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill reads brand material from user-provided 'brand-material packs' and external Google Drive documents (brand culture, website content, industry background, etc.) as described in Step 1 of SKILL.md.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the ingested brand material.
Capability inventory: The agent has access to the google-workspace MCP server, allowing it to search Drive, read file content, and write outputs to Drive subfolders.
Sanitization: No sanitization or validation of the ingested document content is mentioned before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The documentation in SKILL.md includes a command for the user to install the skill from an external repository.
Evidence: npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill seo-persona-builder
[COMMAND_EXECUTION]: The skill utilizes the google-workspace MCP server to interact with the file system (Google Drive).
Evidence: Uses search_drive_files and get_drive_file_content to access organizational data and writes confirmation packets back to Drive.

seo-persona-builder