The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to fetch and process arbitrary content from external URLs (articles, RSS feeds, and transcripts).
Ingestion points: External content enters the agent's context through reader_client.py when using the docs list --with-content command, which retrieves html_content from the Readwise API.
Boundary markers: The skill does not implement delimiters or specific instructions to the agent to disregard instructions found within the fetched document content.
Capability inventory: The skill has the capability to perform network requests and execute local scripts via uv run as defined in SKILL.md.
Sanitization: No evidence of content sanitization or instruction filtering is present in the provided scripts.
[COMMAND_EXECUTION]: The skill relies on uv run for executing its Python-based CLI tool, which involves local command execution within the agent's environment.
[EXTERNAL_DOWNLOADS]: The reader_client.py script makes network calls to the official Readwise API domain (readwise.io) to interact with the Reader service and retrieve document data.

readwise-reader