The Agent Skills Directory

[SAFE]: The skill consists of documentation and configuration templates for GitHub Actions. All referenced actions originate from official or well-known repositories.
[SAFE]: Hardcoded credentials found in the Kotlin/Micronaut workflow template (e.g., POSTGRES_PASSWORD: test) are standard dummy values used for local service containers in testing environments and do not pose a security risk.
[PROMPT_INJECTION]: The skill includes a "PR Babysitting" pattern that reads check statuses using the GitHub CLI. This constitutes an indirect prompt injection surface where the agent processes external data (check names and failure messages). However, this is a necessary function for the skill's stated purpose and no instructions were found that would lead to the unsafe execution of this content.
Ingestion points: gh pr checks <number> command in SKILL.md.
Boundary markers: None used for the output of CLI commands.
Capability inventory: Shell access (Bash tool) and file system access (Write, Edit tools).
Sanitization: No sanitization is performed on the ingested CLI output.

ci-cd-patterns