The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/sync.py executes the readwise CLI tool using subprocess.run. Arguments are passed as a list rather than a single string, which is a security best practice that prevents shell injection vulnerabilities.\n- [EXTERNAL_DOWNLOADS]: The skill relies on the @readwise/cli package, which is the official command-line utility for the Readwise service. This dependency is fetched from the standard NPM registry and is required for API communication.\n- [PROMPT_INJECTION]: The skill ingests external content from the Readwise API, which could theoretically contain malicious instructions. This risk is managed through proper data handling and isolation.\n
Ingestion points: Untrusted data enters via list_documents, list_highlights, and get_document_content in scripts/sync.py.\n
Boundary markers: The script uses Markdown frontmatter delimiters (---) to differentiate metadata from the article content.\n
Capability inventory: The skill is limited to executing the Readwise CLI and writing Markdown files to a specific local directory.\n
Sanitization: Metadata values are escaped for YAML compatibility in the yaml_str function, and filenames are cleaned using the slugify function.

readwise-second-brain-sync