The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and fetches a configuration schema from Google's official GitHub repository (raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json) and utilizes the googleapis/release-please-action@v4 GitHub Action. These originate from a trusted organization and are used for standard configuration validation and workflow execution.
[COMMAND_EXECUTION]: The skill instructs the agent to execute git remote -v to gather information about the repository hosting platform. This is a routine operation for environment discovery in DevOps automation.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from the project's commit history and PR titles to determine versioning and changelog content. * Ingestion points: Git commit logs and Pull Request titles. * Boundary markers: Absent; the agent is not instructed to use specific delimiters or warnings to ignore instructions embedded within commit messages. * Capability inventory: Writing configuration files to the project directory (e.g., GitHub Actions workflows, Azure Pipeline YAML, manifest files) and updating project-local context files. * Sanitization: The skill lacks explicit sanitization or filtering logic for the content of commit messages before processing them for versioning decisions.

release-automation