The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or unauthorized data access was detected. The skill's functionality aligns with its described purpose of PR reviewing.
[EXTERNAL_DOWNLOADS]: The skill automates the installation of the official GitHub CLI (gh) through trusted system package managers (Homebrew and APT).
[COMMAND_EXECUTION]: The skill executes standard development commands such as gh, npm test, npm run lint, and npm audit to validate code quality and security.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests untrusted content from GitHub Pull Requests.
Ingestion points: SKILL.md (via gh pr view and gh pr diff outputs containing PR titles, bodies, and code changes)
Boundary markers: Absent
Capability inventory: Uses gh for PR interactions and npm for local script execution
Sanitization: None

pr-reviewer