The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions for installing official development packages and tools from public registries, including markdownlint-cli via npm, pre-commit via pip, and the linter-markdownlint package for Atom. It also references official GitHub repositories for pre-commit hooks.
[COMMAND_EXECUTION]: The documentation includes numerous shell commands for linting files, configuring CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI, Jenkins, Azure Pipelines), and setting up Docker environments. These commands are standard for the markdownlint ecosystem and follow developer best practices.
[INDIRECT_PROMPT_INJECTION]: The skill documents workflows for processing external markdown files. While this creates a potential attack surface for indirect prompt injection if an agent were to process maliciously crafted markdown files, the skill itself provides standard linting configurations and does not contain any exploitable logic.
Ingestion points: Markdown files processed by the CLI or API (e.g., **/*.md).
Boundary markers: None explicitly defined in the provided configuration examples.
Capability inventory: File reading/writing via Node.js fs module and shell command execution via Bash.
Sanitization: None, as the primary function is static analysis of file content.

markdownlint-integration