The Agent Skills Directory

[SAFE]: The skill provides templates for generating standard GitLab CI/CD pipelines including linting, testing, and deployment stages.
[SAFE]: The templates include remote script execution to install Composer from the official and well-known source https://getcomposer.org/installer.
[SAFE]: Deployment templates use SSH with the -o StrictHostKeyChecking=no flag; this is a common best-practice violation in automated environments and does not indicate malicious intent.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its analysis of untrusted project data.
Ingestion points: The skill analyzes composer.json and existing .gitlab-ci.yml files as part of its project analysis step.
Boundary markers: Absent. There are no instructions to the agent to treat content from project files as untrusted or to use delimiters.
Capability inventory: The skill uses project analysis to decide which tools and configurations to generate in the final pipeline.
Sanitization: Absent. The skill does not mention any validation or filtering of content ingested from the project files.

create-gitlab-ci