X To Kindle

Send X/Twitter posts to Kindle for distraction-free reading. Use when user shares an X/Twitter link and wants to read it on Kindle, or asks to send a tweet/thread to their Kindle device.

This skill appears to implement its stated function, but there are two practical concerns you should consider before installing: 1) Secrets and metadata mismatch: SKILL.md and the script require SMTP_EMAIL, SMTP_PASSWORD (app password), and KINDLE_EMAIL, but the registry metadata lists no required env vars. Do not assume the skill is safe just because metadata omits credentials — the code will need them. 2) Arbitrary-file-sending risk: The included tool will send any local file path you pass to it to the configured Kindle email. That is necessary to send the generated HTML, but it also means a mis-invocation or malicious agent behavior could exfiltrate local files. To reduce risk: - Use a dedicated email account (Gmail) and an app-specific password with minimal access; avoid using your primary account. - Use a disposable or limited-permissions Kindle address if possible. - Only grant SMTP_PASSWORD to skills you trust, and prefer rotating the app password after testing. - Inspect and, if possible, modify the script so it only accepts files from a controlled directory (e.g., a sandboxed /tmp/<skill>/ folder) or validates filenames before sending. - Confirm how your agent platform prompts you (or not) before invoking the tool; require explicit user confirmation for any send operation. - Verify network calls (fxtwitter API) are acceptable for your privacy policy; consider using an API you trust or self-hosted fetch logic. If you cannot or will not follow these mitigations, avoid installing or provide only throwaway credentials for testing.

Type: OpenClaw Skill Name: x-to-kindle Version: 0.1.1 The `send_to_kindle.py` script is designed to send any local file specified by its command-line argument to a pre-configured Kindle email address via SMTP. While the `SKILL.md` instructions limit its intended use to a generated HTML file in `/tmp`, the underlying script's broad file access capability (reading arbitrary files from the filesystem) combined with network exfiltration (emailing the file) presents a significant risk. A malicious prompt could instruct the agent to use this tool to exfiltrate sensitive files (e.g., `~/.ssh/id_rsa`, `/etc/passwd`) to the configured Kindle email, which, while user-controlled, still constitutes unauthorized data exfiltration from the agent's environment.