The Agent Skills Directory

[SAFE]: The skill defines a comprehensive security framework for deployments. It includes explicit guardrails against unauthorized overrides and mandates the use of non-root users in Docker environments.
[EXTERNAL_DOWNLOADS]: Fetches the official uv tool binary from GitHub Container Registry (ghcr.io/astral-sh/uv) within a Docker multi-stage build. This is a reference to a well-known tool from a reputable source.
[COMMAND_EXECUTION]: Utilizes standard operational tools including kubectl, docker, trivy, checkov, and tfsec. These commands are used for their intended purpose of infrastructure validation and deployment management.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from CI/CD logs and monitoring services (Sentry, Datadog). While this represents a potential ingestion surface for untrusted data, the skill includes explicit instructions for the agent to scrub sensitive information (secrets and keys) from its context window and maintains strict human-in-the-loop requirements for sensitive operations.

deployment