The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content from Pull Requests (titles, bodies, and code diffs).
Ingestion points: Reads data using gh pr view, gh pr diff, and git diff in SKILL.md.
Boundary markers: Absent; there are no instructions to the agent to treat PR content as untrusted or to ignore instructions found within the diffs.
Capability inventory: The skill utilizes shell commands (gh, git) and has the ability to read project files.
Sanitization: Absent; no validation or sanitization of external PR data is performed before the agent analyzes it.
[COMMAND_EXECUTION]: The skill executes gh and git CLI commands to retrieve PR information and perform diffing. These tools are used for the skill's primary purpose of code review.

agents-pr-review