The Agent Skills Directory

[COMMAND_EXECUTION]: Uses the @esaio/esa-cli tool to manage esa.io content. The instructions emphasize confirming targets before destructive actions like deletion or archiving.\n- [EXTERNAL_DOWNLOADS]: References the official @esaio/esa-cli Node.js package, which is a trusted resource provided by the vendor (esaio).\n- [DATA_EXFILTRATION]: Interacts with the esa.io API to read and write organizational knowledge. It utilizes environment variables for token management and supports attachment operations.\n- [PROMPT_INJECTION]: Processes untrusted data from the esa.io platform, creating a surface for indirect prompt injection.\n
Ingestion points: Articles and comments are retrieved using esa post view, esa post list, and esa comment list.\n
Boundary markers: The skill does not explicitly define delimiters to isolate external Markdown content within the agent's context.\n
Capability inventory: The skill enables network API calls, file system output for attachments, and shell command execution.\n
Sanitization: No specific content filtering or sanitization steps are documented for ingested data.

esa-cli