What problem does it solve? Leaked credentials in GitHub issues, PRs, comments, and discussions expose the project to compromise, and cleaning them up requires careful redaction, edit-history purging, author notification, and alert resolution across many location types. ## Core Features & Use Cases - Alert Triage and Content Fetching: List open secret scanning alerts and fetch affected content with hide_secret=true so plaintext secrets never appear in terminal output. - Redaction and History Purging: Redact issue/PR bodies in place, or delete and recreate leaked comments (including discussion comments via GraphQL) to wipe edit history. - Notification and Resolution: Post templated English security notices to authors, skip notifications when the body is already redacted, resolve alerts, and produce a formatted summary table. - Use Case: A maintainer receives a GitHub Secret Scanning alert for a Discord bot token posted in an issue comment; the skill fetches the comment, deletes it, recreates a redacted version, notifies the author to rotate the credential, and resolves the alert. ## Quick Start Ask the agent to list all open secret scanning alerts for the openclaw repository and process alert number 72 end to end.