The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill scans, reads, and modifies markdown files across the project directory. If these files contain adversarial instructions (e.g., hidden in comments), the agent might follow them while attempting to 'fix' the file.
Ingestion points: The workflow directs the agent to scan all **/*.md files and perform manual or automatic edits using Phase 2, 4, and 5 instructions.
Boundary markers: Content from target files is not wrapped in protective delimiters or accompanied by instructions to ignore embedded commands.
Capability inventory: The skill utilizes the Bash tool for command execution and has extensive file modification capabilities via Write and Edit tools.
Sanitization: No sanitization or escaping of the content within the markdown files is performed before processing or applying fixes.
[COMMAND_EXECUTION]: The skill uses shell commands for environment setup, diagnostics, and automated fixes. It explicitly instructs the agent to run markdownlint-cli2 and npm install commands to manage the linting environment.
[EXTERNAL_DOWNLOADS]: The skill downloads the markdownlint-cli2 package from the public NPM registry if it is not already installed on the system.

markdown-linter-fixer