The Agent Skills Directory

[SAFE]: No malicious command execution, data exfiltration, or persistence mechanisms were detected. The skill uses standard GitHub CLI commands for its operations.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from GitHub issues. * Ingestion points: Issue title and body fetched via gh issue view. * Boundary markers: None explicitly defined to separate untrusted content from instructions. * Capability inventory: Write access to GitHub issues via gh issue edit. * Sanitization: None. The risk is mitigated by the mandatory human review step requiring the user to confirm the diff before the issue is updated.
[SAFE]: The installation process uses the author's official repository, and the workflow is transparent with a dry-run mode and explicit confirmation prompts.

refine-issue