The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to perform actions such as creating, editing, and commenting on pull requests. These commands are necessary for the skill's functionality and are used according to standard repository management practices.
[INDIRECT_PROMPT_INJECTION]: The skill processes external, repository-controlled configuration files which presents a surface for indirect prompt injection. * Ingestion points: The agent is instructed to read and interpret .coderabbit.yaml, .coderabbit.yml, and greptile.json from the target repository to determine how to apply AI review labels and comments. * Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within these external configuration files. * Capability inventory: The skill possesses the ability to execute shell commands (gh) and write data to the repository's pull requests based on its interpretation of the configuration files. * Sanitization: The skill lacks explicit sanitization or strict schema validation for the data ingested from these repository configuration files, relying on the agent to parse specific keys for review policy logic.

create-pr