The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the use of standard development tools including git and gh (GitHub CLI) to automate branch management, staging, committing, and pull request lifecycle operations.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process untrusted data from external sources.
Ingestion points: The workflow in references/review.md fetches remote content such as pull request descriptions, metadata, and code diffs using gh pr view and gh pr diff commands.
Boundary markers: No specific delimiters or instructions are used to isolate the ingested external PR content from the agent's internal instruction set.
Capability inventory: Across the reference files, the skill has the capability to execute state-changing shell commands including git commit, git push, and gh pr create based on the context it processes.
Sanitization: There are no explicit sanitization or validation steps mentioned for the content retrieved from the GitHub repository before it is processed by the agent.

pr